{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:14:08Z","timestamp":1784178848503,"version":"3.55.0"},"reference-count":243,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,1,25]],"date-time":"2025-01-25T00:00:00Z","timestamp":1737763200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,1,25]],"date-time":"2025-01-25T00:00:00Z","timestamp":1737763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Talent Introduction Program of Hubei Polytechnic University","award":["23xjz14R"],"award-info":[{"award-number":["23xjz14R"]}]},{"name":"2023 Joint Open Fund for Hubei Key Laboratory of Mine Environmental Pollution Control & Remedition, Hubei Polytechnic University and Huangshi Daye Lake National Hi-tech Development Zone Science Park","award":["23xjz08AK"],"award-info":[{"award-number":["23xjz08AK"]}]},{"name":"2023 Hubei Provincial Department of Education Scientific Research Plan Guiding Project","award":["B2023234"],"award-info":[{"award-number":["B2023234"]}]},{"name":"2023 Hubei Polytechnic University-Wuhan Nanhua Industrial Equipments Engineering Co., Ltd. Joint Laboratory Open Fund"},{"name":"Hubei Provincial Science and Technology Plan Project","award":["KJRQ2023000110"],"award-info":[{"award-number":["KJRQ2023000110"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61871178"],"award-info":[{"award-number":["61871178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"DOI":"10.1007\/s10462-025-11110-3","type":"journal-article","created":{"date-parts":[[2025,1,25]],"date-time":"2025-01-25T08:01:26Z","timestamp":1737792086000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":59,"title":["Comprehensive exploration of diffusion models in image generation: a survey"],"prefix":"10.1007","volume":"58","author":[{"given":"Hang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meilin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,25]]},"reference":[{"key":"11110_CR1","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal (2021) Improved denoising diffusion probabilistic models. In International conference on machine learning, pp 8162\u20138171"},{"key":"11110_CR2","doi-asserted-by":"publisher","first-page":"104153","DOI":"10.1109\/ACCESS.2024.3393842","volume":"12","author":"Raza Syed Ali","year":"2024","unstructured":"Ali Raza Syed, Usman Habib, Muhammad Usman, Ashraf Cheema Adeel, Sajid Khan Muhammad (2024) MMGANGUARD: a robust approach for detecting fake images generated by GANS using multi-model techniques. IEEE Access 12:104153\u2013104164","journal-title":"IEEE Access"},{"key":"11110_CR3","doi-asserted-by":"crossref","unstructured":"Anciukevicius Titas, Xu Zexiang, Fisher Matthew, Henderson Paul, Bilen Hakan, Mitra Niloy J, Guerrero Paul (2023) Renderdiffusion: Image diffusion for 3D reconstruction, inpainting and generation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12608\u201312618","DOI":"10.1109\/CVPR52729.2023.01213"},{"issue":"3","key":"11110_CR4","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/0304-4149(82)90051-5","volume":"12","author":"DO Anderson Brian","year":"1982","unstructured":"Anderson Brian DO (1982) Reverse-time diffusion equation models. Stochast Process Appl 12(3):313\u2013326","journal-title":"Stochast Process Appl"},{"key":"11110_CR5","unstructured":"Arjovsky Mart\u00edn, Chintala Soumith, Bottou L\u00e9on (2017) Wasserstein generative adversarial networks. In Proceedings of the 34th International Conference on Machine Learning, vol 70, pp 214\u2013223"},{"key":"11110_CR6","doi-asserted-by":"crossref","unstructured":"Asnani Vishal, Collomosse John,\u00a0Bui Tu, Liu Xiaoming, Agarwal Shruti (2024) Promark: Proactive diffusion watermarking for causal attribution. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 10802\u201310811","DOI":"10.1109\/CVPR52733.2024.01027"},{"key":"11110_CR7","unstructured":"Austin Jacob, Johnson Daniel D., Ho Jonathan, Tarlow Daniel, Berg Rianne van den (2021) Structured denoising diffusion models in discrete state-spaces. In Advances in Neural Information Processing Systems, pp 17981\u201317993"},{"key":"11110_CR8","doi-asserted-by":"crossref","unstructured":"Bansal Hritik,\u00a0Yin Da, Monajatipoor Masoud, Chang Kai-Wei (2022) How well can text-to-image generative models understand ethical natural language interventions? Preprint at arXiv:2210.15230","DOI":"10.18653\/v1\/2022.emnlp-main.88"},{"key":"11110_CR9","doi-asserted-by":"crossref","unstructured":"Bao Qiqi, Hui Zheng, Zhu Rui, Ren Peiran, Xie Xuansong, Yang Wenming (2024) Improving diffusion-based image restoration with error contraction and error correction. In Thirty-Eighth AAAI Conference on Artificial Intelligence, pp 756\u2013764","DOI":"10.1609\/aaai.v38i2.27833"},{"key":"11110_CR10","doi-asserted-by":"crossref","unstructured":"Ben Fei, Zhaoyang Lyu, Liang Pan, Junzhe Zhang, Weidong Yang, Tianyue Luo, Bo Zhang, Bo Dai (2023) Generative diffusion prior for unified image restoration and enhancement. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition 55:9935\u20139946","DOI":"10.1109\/CVPR52729.2023.00958"},{"key":"11110_CR11","unstructured":"Betker James, Goh Gabriel, Jing Li, et. al. Improving image generation with better captions. https:\/\/api.semanticscholar.org\/CorpusID:264403242"},{"key":"11110_CR12","doi-asserted-by":"crossref","unstructured":"Blattmann Andreas, Rombach Robin, Ling Huan, Dockhorn Tim, Kim Seung Wook, Fidler Sanja, Kreis Karsten (2023) Align your latents: High-resolution video synthesis with latent diffusion models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023, pp 22563\u201322575","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"11110_CR13","doi-asserted-by":"crossref","unstructured":"Boutros Fadi, Grebe Jonas Henry, Kuijper Arjan, Damer Naser (2023) Idiff-face: Synthetic-based face recognition through fizzy identity-conditioned diffusion model. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 19650\u201319661","DOI":"10.1109\/ICCV51070.2023.01800"},{"key":"11110_CR14","unstructured":"Brack Manuel, Friedrich Felix, Schramowski Patrick, Kersting Kristian (2023) Mitigating inappropriateness in image generation: Can there be value in reflecting the world\u2019s ugliness? Preprint at arXiv:2305.18398"},{"key":"11110_CR15","unstructured":"Brack Manuel, Schramowski Patrick, Friedrich Felix, Hintersdorf Dominik, Kersting Kristian (2022) The stable artist: Steering semantics in diffusion latent space. Preprint at arXiv:2212.06013"},{"key":"11110_CR16","doi-asserted-by":"crossref","unstructured":"Brack Manuel, Schramowski Patrick, Kersting Kristian (2023) Distilling adversarial prompts from safety benchmarks: Report for the adversarial nibbler challenge. Preprint at arXiv:2309.11575","DOI":"10.18653\/v1\/2023.artofsafety-1.3"},{"key":"11110_CR17","unstructured":"Cao Pu, Zhou Feng, Song Qing,\u00a0Yang Lu (2024) Controllable generation with text-to-image diffusion models: A survey. Preprint at arXiv:2403.04279"},{"key":"11110_CR18","unstructured":"Carlini Nicolas, Hayes Jamie, Nasr Milad, Jagielski Matthew, Sehwag Vikash, Tramer Florian, Balle Borja, Ippolito Daphne, Wallace Eric (2023) Extracting training data from diffusion models. In 32nd USENIX Security Symposium (USENIX Security 23), pp 5253\u20135270"},{"key":"11110_CR19","unstructured":"Casper Stephen, Guo Zifan, Mogulothu Shreya, Marinov Zachary, Deshpande Chinmay, Yew Rui-Jie, Dai Zheng, Hadfield-Menell Dylan (2023) Measuring the success of diffusion models at imitating human artists. Preprint at arXiv:2307.04028"},{"key":"11110_CR20","doi-asserted-by":"crossref","unstructured":"Cazenavette George, Sud Avneesh, Leung Thomas, Usman Ben (2024) Fakeinversion: Learning to detect images from unseen text-to-image models by inverting stable diffusion. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024, pp 10759\u201310769","DOI":"10.1109\/CVPR52733.2024.01023"},{"key":"11110_CR21","unstructured":"Chang Ziyi, Koulieris George Alex, Shum Hubert P.\u00a0H (2023) On the design fundamentals of diffusion models: A survey. Preprint at arXiv:2306.04542"},{"key":"11110_CR22","unstructured":"Chen Dar-Yen (2023) Artfusion: Controllable arbitrary style transfer using dual conditional latent diffusion models. Preprint at arXiv:2306.09330"},{"key":"11110_CR23","doi-asserted-by":"crossref","unstructured":"Chen Jingyi , Wang Xiaolong, He Zhijian, Peng Xiaojiang (2024) A comprehensive exploration on detecting fake images generated by stable diffusion. In Pattern Recognition and Computer Vision - 7th Chinese Conference, PRCV 2024, Urumqi, China, October 18-20, 2024, Proceedings, Part I, volume 15031 of Lecture Notes in Computer Science, pp 461\u2013475","DOI":"10.1007\/978-981-97-8487-5_32"},{"key":"11110_CR24","doi-asserted-by":"crossref","unstructured":"Chen Songyan, Huang Jiancheng (2023) Fec: Three finetuning-free methods to enhance consistency for real image editing. In 2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), pp 76\u201387","DOI":"10.1109\/ICICML60161.2023.10424833"},{"key":"11110_CR25","unstructured":"Chen Zheng, Zhang Yulun, Liu Ding, Gu Jinjin, Kong Linghe, Yuan Xin et al (2024) Hierarchical integration diffusion model for realistic image deblurring. Adv Neural Inform Process Syst 36"},{"key":"11110_CR26","unstructured":"Cheng Lu, Kaiwen Zheng, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu (2022) Maximum likelihood training for score-based diffusion odes by high order denoising score matching. In International Conference on Machine Learning vol 162, pp 14429\u201314460"},{"key":"11110_CR27","doi-asserted-by":"crossref","unstructured":"Cheng Ta-Ying, Gadelha Matheus, Groueix Thibault, Fisher Matthew, Mech Radomir, Markham Andrew, Trigoni Niki (2024) Learning continuous 3d words for text-to-image generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6753\u20136762","DOI":"10.1109\/CVPR52733.2024.00645"},{"key":"11110_CR28","doi-asserted-by":"crossref","unstructured":"Chenlu Zhan Yu, Lin Gaoang Wang, Wang Hongwei, Jian Wu (2024) Medm2g: Unifying medical multi-modal generation via cross-guided diffusion with visual invariant. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 11502\u201311512","DOI":"10.1109\/CVPR52733.2024.01093"},{"key":"11110_CR29","unstructured":"Chin Zhi-Yi, Jiang Chieh-Ming, Huang Ching-Chun, Chen Pin-Yu, Chiu Wei-Chen (2023) Prompting4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts. Preprint at arXiv:2309.06135"},{"issue":"4","key":"11110_CR30","first-page":"4713","volume":"45","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, Fleet David J, Mohammad Norouzi (2022) Image super-resolution via iterative refinement. IEEE Trans Pattern Anal Mach Intell 45(4):4713\u20134726","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11110_CR31","unstructured":"Choi Jooyoung, Choi Yunjey, Kim Yunji, Kim Junho, Yoon Sungroh (2023) Custom-edit: Text-guided image editing with customized diffusion models. Preprint at arXiv:2305.15779"},{"issue":"5","key":"11110_CR32","doi-asserted-by":"publisher","first-page":"5018","DOI":"10.1103\/PhysRevE.56.5018","volume":"56","author":"Jarzynski Christopher","year":"1997","unstructured":"Christopher Jarzynski (1997) Equilibrium free-energy differences from nonequilibrium measurements: a master-equation approach. Phys Rev E 56(5):5018","journal-title":"Phys Rev E"},{"key":"11110_CR33","doi-asserted-by":"crossref","unstructured":"Chung Jiwoo, Hyun Sangeek, Heo Jae-Pil (2023) Style injection in diffusion: A training-free approach for adapting large-scale diffusion models for style transfer. Preprint at arXiv:2312.09008","DOI":"10.1109\/CVPR52733.2024.00840"},{"issue":"140","key":"11110_CR34","first-page":"1","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Liu Peter J (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(140):1\u201367","journal-title":"J Mach Learn Res"},{"key":"11110_CR35","unstructured":"De Simone Zoe, Boggust Angie, Satyanarayan Arvind, Wilson Ashia (2023) What is a fair diffusion model? designing generative text-to-image models to incorporate various worldviews. Preprint at arXiv:2309.09944"},{"key":"11110_CR36","doi-asserted-by":"crossref","unstructured":"Deng Yingying, He Xiangyu, Tang Fan, Dong Weiming (2023) Z$$^{\\text{*}}$$: Zero-shot style transfer via attention rearrangement. Preprint at arXiv:2311.16491","DOI":"10.1109\/CVPR52733.2024.00662"},{"issue":"10","key":"11110_CR37","doi-asserted-by":"publisher","first-page":"6024","DOI":"10.1109\/TPAMI.2021.3085766","volume":"44","author":"Fan Deng-Ping","year":"2022","unstructured":"Deng-Ping Fan, Ge-Peng Ji, Ming-Ming Cheng, Ling Shao (2022) Concealed object detection. IEEE Trans Pattern Anal Mach Intell 44(10):6024\u20136042","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11110_CR38","unstructured":"Dhariwal Prafulla, Nichol Alexander Quinn (2021) Diffusion models beat gans on image synthesis. In Advances in Neural Information Processing Systems, pp 8780\u20138794"},{"key":"11110_CR39","unstructured":"Dmitry Baranchuk, Andrey Voynov, Ivan Rubachev, Valentin Khrulkov, Artem Babenko (2022) Label-efficient semantic segmentation with diffusion models"},{"key":"11110_CR40","doi-asserted-by":"crossref","unstructured":"Dong Wenkai, Xue Song, Duan Xiaoyue, Han Shumin (2023) Prompt tuning inversion for text-driven image editing using diffusion models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 7430\u20137440","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"11110_CR41","doi-asserted-by":"crossref","unstructured":"Dubinski Jan, Kowalczuk Antoni, Pawlak Stanisaw, Rokita Przemyslaw, Trzciski Tomasz, Morawiecki Pawe (2024) Towards more realistic membership inference attacks on large diffusion models. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 4860\u20134869","DOI":"10.1109\/WACV57701.2024.00479"},{"key":"11110_CR42","unstructured":"Dumoulin Vincent, Shlens Jonathon, Kudlur Manjunath (2017) A learned representation for artistic style. In 5th International Conference on Learning Representations"},{"key":"11110_CR43","unstructured":"Esser Patrick, Kulal Sumith, Blattmann Andreas, Entezari Rahim,\u00fcller Jonas M, Saini Harry, Levi Yam, Lorenz Dominik, Sauer Axel, Boesel Frederic, Podell Dustin, Dockhorn Tim, English Zion, Rombach Robin (2024) Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024"},{"issue":"5","key":"11110_CR44","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1002\/ima.22890","volume":"33","author":"Goceri Evgin","year":"2023","unstructured":"Evgin Goceri (2023) Comparison of the impacts of dermoscopy image augmentation methods on skin cancer classification and a new augmentation method with wavelet packets. Int J Imaging Syst Technol 33(5):1727\u20131744","journal-title":"Int J Imaging Syst Technol"},{"issue":"9","key":"11110_CR45","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/s10462-024-10897-x","volume":"57","author":"Goceri Evgin","year":"2024","unstructured":"Evgin Goceri (2024) GAN based augmentation using a hybrid loss function for dermoscopy images. Artif Intell Rev 57(9):234","journal-title":"Artif Intell Rev"},{"key":"11110_CR46","unstructured":"Fan Bao, Chongxuan Li, Jun Zhu, Bo Zhang (2022) Analytic-DPM: an analytic estimate of the optimal reverse variance in diffusion probabilistic models"},{"key":"11110_CR47","doi-asserted-by":"crossref","unstructured":"Fan Deng-Ping, Ji Ge-Peng, Xu Peng, Cheng Ming-Ming, Sakaridis Christos, Gool Luc Van (2023) Advances in deep concealed scene understanding. Vis Intell 1(1)","DOI":"10.1007\/s44267-023-00019-6"},{"key":"11110_CR48","unstructured":"Fan Mingyuan, Wang Chengyu, Chen Cen, Liu Yang, Huang Jun (2024) On the trustworthiness landscape of state-of-the-art generative models: a survey and outlook. Preprint at arXiv:2307.16680"},{"key":"11110_CR49","doi-asserted-by":"crossref","unstructured":"Fan Yuheng, Liao Hanxi, Huang Shiqi, Luo Yimin, Fu Huazhu, Qi Haikun (2023) A survey of emerging applications of diffusion probabilistic models in MRI. Preprint at arXiv:2311.11383","DOI":"10.1016\/j.metrad.2024.100082"},{"issue":"9","key":"11110_CR50","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"Croitoru Florinel-Alin","year":"2023","unstructured":"Florinel-Alin Croitoru, Vlad Hondru, Tudor Ionescu Radu, Mubarak Shah (2023) Diffusion models in vision: a survey. IEEE Trans Pattern Anal Mach Intell 45(9):10850\u201310869","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"11110_CR51","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"Croitoru Florinel-Alin","year":"2023","unstructured":"Florinel-Alin Croitoru, Vlad Hondru, Tudor Ionescu Radu, Mubarak Shah (2023) Diffusion models in vision: a survey. IEEE Trans Pattern Anal Mach Intell 45(9):10850\u201310869","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11110_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104143","volume":"249","author":"Tassone Francesco","year":"2024","unstructured":"Francesco Tassone, Luca Maiano, Irene Amerini (2024) Continuous fake media detection: adapting deepfake detectors to new generative techniques. Comput Vis Image Underst 249:104143","journal-title":"Comput Vis Image Underst"},{"key":"11110_CR53","doi-asserted-by":"crossref","unstructured":"Friedrich Felix, Brack Manuel, Struppek Lukas, Hintersdorf Dominik, Schramowski Patrick, Luccioni Sasha, Kersting Kristian (2023) Fair diffusion: Instructing text-to-image generation models on fairness. Preprint at arXiv:2302.10893","DOI":"10.1007\/s43681-024-00531-5"},{"key":"11110_CR54","doi-asserted-by":"crossref","unstructured":"Gandikota Kanchana Vaishnavi,Chandramouli Paramanand (2024) Text-guided explorable image super-resolution. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 25900\u201325911","DOI":"10.1109\/CVPR52733.2024.02447"},{"key":"11110_CR55","doi-asserted-by":"crossref","unstructured":"Gandikota Rohit, Orgad Hadas, Belinkov Yonatan, Materzy\u0144ska Joanna, Bau David (2024) Unified concept editing in diffusion models. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 5111\u20135120","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"11110_CR56","doi-asserted-by":"crossref","unstructured":"Ganguli Deep, Hernandez Danny, Lovitt Liane, Askell Amanda, Bai Yuntao, Chen Anna, Conerly Tom, DasSarma Nova, Drain Dawn, Elhage Nelson, Showk Sheer El, Fort Stanislav, Hatfield-Dodds Zac, Henighan Tom, Johnston Scott, Jones Andy, Joseph Nicholas, Kernian Jackson, Kravec Shauna, Mann Ben, Nanda Neel, Ndousse Kamal, Olsson Catherine, Amodei Daniela, Brown Tom B., Kaplan Jared, McCandlish Sam, Olah Christopher, Amodei Dario, Clark Jack (2022) Predictability and surprise in large generative models. In FAccT \u201922: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21 - 24, 2022, pp 1747\u20131764","DOI":"10.1145\/3531146.3533229"},{"key":"11110_CR57","doi-asserted-by":"crossref","unstructured":"Gao Sicheng, Liu Xuhui, Zeng Bohan, Xu Sheng, Li Yanjing, Luo Xiaoyan, Liu Jianzhuang, Zhen Xiantong, Zhang Baochang (2023) Implicit diffusion models for continuous super-resolution. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10021\u201310030","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"11110_CR58","unstructured":"Gatys Leon A, Ecker Alexander S, Bethge Matthias (c) A neural algorithm of artistic style. Preprint at arXiv:1508.06576"},{"issue":"8\/9","key":"11110_CR59","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1007\/s003710050148","volume":"14","author":"Wolberg George","year":"1998","unstructured":"George Wolberg (1998) Image morphing: a survey. Vis Comput 14(8\/9):360\u2013372","journal-title":"Vis Comput"},{"key":"11110_CR60","first-page":"1","volume":"57","author":"Papamakarios George","year":"2021","unstructured":"George Papamakarios, Nalisnick Eric T, Jimenez Rezende Danilo, Shakir Mohamed, Balaji Lakshminarayanan (2021) Normalizing flows for probabilistic modeling and inference. J Mach Learn Res 57:1\u201357","journal-title":"J Mach Learn Res"},{"issue":"3","key":"11110_CR61","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/0550-3213(81)90056-0","volume":"180","author":"Parisi Giorgio","year":"1981","unstructured":"Giorgio Parisi (1981) Correlation functions and computer simulations. Nucl Phys B 180(3):378\u2013384","journal-title":"Nucl Phys B"},{"key":"11110_CR62","unstructured":"Goodfellow Ian J, Pouget-Abadie Jean, Mirza Mehdi, Xu Bing, Warde-Farley David, Ozair Sherjil, Courville Aaron C, Bengio Yoshua (2014) Generative adversarial nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems, pp 2672\u20132680"},{"issue":"4","key":"11110_CR63","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1111\/j.2517-6161.1994.tb02000.x","volume":"56","author":"Ulf Grenander","year":"1994","unstructured":"Grenander Ulf, Miller Michael I (1994) Representations of knowledge in complex systems. J Roy Stat Soc: Ser B (Methodol) 56(4):549\u2013581","journal-title":"J Roy Stat Soc: Ser B (Methodol)"},{"key":"11110_CR64","unstructured":"Gu Jing, Wang Yilin, Zhao Nanxuan, Fu Tsu-Jui, Xiong Wei, Liu Qing, Zhang Zhifei,\u00a0Zhang He, Zhang Jianming, Jung HyunJoon et al (2024) Photoswap: Personalized subject swapping in images. Adv Neural Inform Process Sys 36"},{"key":"11110_CR65","unstructured":"Gu Xiangming, Du Chao, Pang Tianyu, Li Chongxuan, Lin Min,\u00a0Wang Ye (2024) On memorization in diffusion models. Preprint at arXiv:2310.02664"},{"key":"11110_CR66","unstructured":"Guanhua Zhang, Jiabao Ji, Yang Zhang, Mo Yu, Jaakkola Tommi S, Shiyu Chang (2023) Towards coherent image inpainting using denoising diffusion implicit models. In International Conference on Machine Learning vol 202, pp 41164\u201341193"},{"key":"11110_CR67","doi-asserted-by":"crossref","unstructured":"Han Ligong, Wen Song, Chen Qi, Zhang Zhixing, Song Kunpeng, Ren Mengwei, Gao Ruijiang, Stathopoulos Anastasis, He Xiaoxiao, Chen Yuxiao et al (2024) Proxedit: Improving tuning-free real image editing with proximal guidance. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 4291\u20134301","DOI":"10.1109\/WACV57701.2024.00424"},{"issue":"7","key":"11110_CR68","doi-asserted-by":"publisher","first-page":"2814","DOI":"10.1109\/TKDE.2024.3361474","volume":"36","author":"Cao Hanqun","year":"2024","unstructured":"Hanqun Cao, Cheng Tan, Zhangyang Gao, Yilun Xu, Guangyong Chen, Pheng-Ann Heng, Stan Z. Li. (2024) A survey on generative diffusion models. IEEE Trans Knowl Data Eng 36(7):2814\u20132830","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"11110_CR69","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neucom.2022.01.029","volume":"479","author":"Li Haoying","year":"2022","unstructured":"Haoying Li, Yifan Yang, Meng Chang, Shiqi Chen, Huajun Feng, Zhihai Xu, Qi Li, Yueting Chen (2022) SRDIFF: Single image super-resolution with diffusion probabilistic models. Neurocomputing 479:47\u201359","journal-title":"Neurocomputing"},{"key":"11110_CR70","unstructured":"Heng Alvin, Soh Harold (2024) Selective amnesia: A continual learning approach to forgetting in deep generative models. Adv Neural Inform Process Syst 36"},{"key":"11110_CR71","unstructured":"Higgins Irina, Matthey Lo\u00efc, Pal Arka, Burgess Christopher P., Glorot Xavier, Botvinick Matthew M, Mohamed Shakir, Lerchner Alexander (2017) beta-vae: Learning basic visual concepts with a constrained variational framework. In 5th International Conference on Learning Representations"},{"key":"11110_CR72","unstructured":"Ho Jonathan, Salimans Tim (2022) Classifier-free diffusion guidance. Preprint at arXiv:2207.12598"},{"key":"11110_CR73","unstructured":"Ho Jonathan, Salimans Tim (2022) Classifier-free diffusion guidance. Preprint at arXiv:2207.12598"},{"key":"11110_CR74","doi-asserted-by":"crossref","unstructured":"Hong Seunghoo, Lee Juhun, Woo Simon S (2024) All but one: Surgical concept erasing with model preservation in text-to-image diffusion models. In Proceedings of the AAAI Conference on Artificial Intelligence 38:21143\u201321151","DOI":"10.1609\/aaai.v38i19.30107"},{"key":"11110_CR75","unstructured":"Hongkai Zheng, Weili Nie, Arash Vahdat, Kamyar Azizzadenesheli, Anima Anandkumar (2023) Fast sampling of diffusion models via operator learning. In International Conference on Machine Learning vol 202, pp 42390\u201342402"},{"key":"11110_CR76","unstructured":"Hu Edward J, Shen Yelong, Wallis Phillip, Allen-Zhu Zeyuan, Li Yuanzhi, Wang Shean,\u00a0Wang Lu, Chen Weizhu (2022) Lora: Low-rank adaptation of large language models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022"},{"key":"11110_CR77","doi-asserted-by":"crossref","unstructured":"Hu Hailong, Pang Jun (2023) Loss and likelihood based membership inference of diffusion models. In International Conference on Information Security, pp 121\u2013141","DOI":"10.1007\/978-3-031-49187-0_7"},{"key":"11110_CR78","unstructured":"Huang Chin-Wei, Lim Jae Hyun, Aaron C (2021) Courville. A variational perspective on diffusion-based generative models and score matching. In Advances in Neural Information Processing Systems, pp 22863\u201322876"},{"key":"11110_CR79","doi-asserted-by":"crossref","unstructured":"Huang Jiancheng, Liu Yifan, Qin Jin, Chen Shifeng (2023). Kv inversion: Kv embeddings learning for text-conditioned real image action editing. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp 172\u2013184. Springer","DOI":"10.1007\/978-981-99-8429-9_14"},{"key":"11110_CR80","unstructured":"Huang Nisha, Zhang Yuxin, Tang Fan, Ma Chongyang, Huang Haibin, Zhang Yong, Dong Weiming, Xu Changsheng (2022) Diffstyler: Controllable dual diffusion for text-driven image stylization. Preprint at arXiv:2211.10682"},{"key":"11110_CR81","doi-asserted-by":"crossref","unstructured":"Hudson Drew A, Zoran Daniel, Malinowski Mateusz, Lampinen Andrew K, Jaegle Andrew, McClelland James L, Matthey Loic, Hill Felix, Lerchner Alexander (2024) Soda: Bottleneck diffusion models for representation learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 23115\u201323127","DOI":"10.1109\/CVPR52733.2024.02181"},{"key":"11110_CR82","unstructured":"Hyvarinen Aapo, Dayan Peter (2005) Estimation of non-normalized statistical models by score matching. J Mach Learn Res 6(4)"},{"key":"11110_CR83","unstructured":"Imagen 3 Team:\u00a0Jason Baldridge, Jakob Bauer, Mukul Bhutani, and et. al. (2024) Imagen 3. Preprint at arXiv:2408.07009"},{"key":"11110_CR84","doi-asserted-by":"crossref","unstructured":"Jia-Hao Wu, Tsai Fu-Jen, Peng Yan-Tsung, Tsai Chung-Chi, Lin Chia-Wen, Lin Yen-Yu (2024) Id-blau: Image deblurring by implicit diffusion-based reblurring augmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 25847\u201325856","DOI":"10.1109\/CVPR52733.2024.02442"},{"key":"11110_CR85","unstructured":"Jiang Yue, Lyu Yueming, Ma Tianxiang,\u00a0Peng Bo, Dong Jing (2023) Rs-corrector: Correcting the racial stereotypes in latent diffusion models. Preprint at arXiv:2312.04810"},{"key":"11110_CR86","doi-asserted-by":"crossref","unstructured":"Jiayi Liao Xu, Chen Qiang Fu, Lun Du, He Xiangnan, Wang Xiang, Han Shi, Zhang Dongmei (2024) Text-to-image generation for abstract concepts. In Thirty-Eighth AAAI Conference on Artificial Intelligence, pp 3360\u20133368","DOI":"10.1609\/aaai.v38i4.28122"},{"key":"11110_CR87","unstructured":"Jolicoeur-Martineau Alexia, Piche-Taillefer Remi, Tachet des Combes Remi, Mitliagkas Ioannis (2020) Adversarial score matching and improved sampling for image generation. Preprint at arXiv:2009.05475"},{"key":"11110_CR88","first-page":"6840","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, Pieter Abbeel (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33:6840\u20136851","journal-title":"Adv Neural Inf Process Syst"},{"key":"11110_CR89","doi-asserted-by":"crossref","unstructured":"Ju Xuan, Zeng Ailing, Zhao Chenchen, Wang Jianan, Zhang Lei, Xu Qiang (2023) Humansd: A native skeleton-guided diffusion model for human image generation. In IEEE\/CVF International Conference on Computer Vision, pp 15942\u201315952","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"11110_CR90","doi-asserted-by":"crossref","unstructured":"Justin Johnson, Alexandre Alahi, Li Fei-Fei (2016) Perceptual losses for real-time style transfer and super-resolution. In Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling, editors, Computer Vision - ECCV 2016\u201314th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016. Proceedings, Part II vol 9906, pp 694\u2013711","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"11110_CR91","unstructured":"Kaiwen Zheng, Cheng Lu, Jianfei Chen, Jun Zhu (2023) Improved techniques for maximum likelihood estimation for diffusion odes. In International Conference on Machine Learning vol 202, pp 42363\u201342389"},{"key":"11110_CR92","doi-asserted-by":"crossref","unstructured":"Ke Bingxin, Obukhov Anton, Huang Shengyu, Metzger Nando, Daudt Rodrigo Caye, Schindler Konrad (2024) Repurposing diffusion-based image generators for monocular depth estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9492\u20139502","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"11110_CR93","unstructured":"Kim Sunwoo, Jang Wooseok, Kim Hyunsu, Kim Junho, Choi Yunjey, Kim Seungryong, Lee Gayeong (2023) User-friendly image editing with minimal text input: Leveraging captioning and injection techniques. Preprint at arXiv:2306.02717,"},{"key":"11110_CR94","unstructured":"Kingma Diederik P, Salimans Tim, Poole Ben, Ho Jonathan (2021) Variational diffusion models. Preprint at arXiv:2107.00630"},{"key":"11110_CR95","unstructured":"Kingma Diederik P, Welling Max (2014) Auto-encoding variational bayes. In 2nd International Conference on Learning Representations"},{"key":"11110_CR96","unstructured":"Kingma Diederik P, Welling Max (2014) Auto-encoding variational bayes. In 2nd International Conference on Learning Representations"},{"key":"11110_CR97","doi-asserted-by":"crossref","unstructured":"Kocsis Peter, Sitzmann Vincent, Nie\u00dfner Matthias (2024) Intrinsic image diffusion for indoor single-view material estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 5198\u20135208","DOI":"10.1109\/CVPR52733.2024.00497"},{"key":"11110_CR98","doi-asserted-by":"crossref","unstructured":"Kumari Nupur, Zhang Bingliang, Wang Sheng-Yu, Shechtman Eli, Zhang Richard, Zhu Jun-Yan (2023) Ablating concepts in text-to-image diffusion models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 22691\u201322702","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"11110_CR99","unstructured":"Lee Jumin, Im Woobin, Lee Sebin, Yoon Sung-Eui (2023) Diffusion probabilistic models for scene-scale 3d categorical data. Preprint at arXiv:2301.00527"},{"issue":"1","key":"11110_CR100","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1631\/FITEE.2300310","volume":"25","author":"Lin Lequan","year":"2024","unstructured":"Lequan Lin, Zhengkun Li, Ruikun Li, Xuliang Li, Junbin Gao (2024) Diffusion models for time-series applications: a survey. Front Inf Technol Electron Eng 25(1):19\u201341","journal-title":"Front Inf Technol Electron Eng"},{"key":"11110_CR101","unstructured":"Li Jia, Hu Lijie, Zhang Jingfeng, Zheng Tianhang, Zhang Hua,\u00a0Wang Di (2023) Fair text-to-image diffusion via fair mapping. Preprint at arXiv:2311.17695"},{"key":"11110_CR102","unstructured":"Li Shengmeng, Liu Luping, Chai Zenghao, Li Runnan,\u00a0Tan Xu (2023) Era-solver: Error-robust adams solver for fast sampling of diffusion probabilistic models. Preprint at arXiv:2301.12935"},{"key":"11110_CR103","doi-asserted-by":"crossref","unstructured":"Li Sifei, Zhang Yuxin, Tang Fan, Ma Chongyang, Dong Weiming, Xu Changsheng (2024) Music style transfer with time-varying inversion of diffusion models. In Thirty-Eighth AAAI Conference on Artificial Intelligence, pp 547\u2013555","DOI":"10.1609\/aaai.v38i1.27810"},{"key":"11110_CR104","unstructured":"Li Tianle, Ku Max, Wei Cong, Chen Wenhu (2023) Dreamedit: Subject-driven image editing. Preprint at arXiv:2306.12624"},{"key":"11110_CR105","unstructured":"Li Xin, Ren Yulin, Jin Xin, Lan Cuiling, Wang Xingrui, Zeng Wenjun, Wang Xinchao, Chen Zhibo (2023) Diffusion models for image restoration and enhancement\u2014a comprehensive survey. Preprint at arXiv:2308.09388"},{"key":"11110_CR106","doi-asserted-by":"crossref","unstructured":"Li Xinghui, Jingyi Lu, Han Kai, Prisacariu Victor Adrian (2024) Sd4match: Learning to prompt stable diffusion model for semantic matching. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 27558\u201327568","DOI":"10.1109\/CVPR52733.2024.02602"},{"key":"11110_CR107","doi-asserted-by":"crossref","unstructured":"Liang Youwei, He Junfeng, Li Gang, Li Peizhao, Klimovskiy Arseniy, Carolan Nicholas, Sun Jiao, Pont-Tuset Jordi, Young Sarah, Yang Feng, Ke Junjie, Dvijotham Krishnamurthy Dj, Collins Katherine M, Luo Yiwen, Li Yang, Kohlhoff Kai J, Ramachandran Deepak, Navalpakkam Vidhya (2024) Rich human feedback for text-to-image generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 19401\u201319411","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"11110_CR108","doi-asserted-by":"crossref","unstructured":"Lin Xinqi, He Jingwen, Chen Ziyan, Lyu Zhaoyang, Fei Ben,\u00a0Dai Bo, Ouyang Wanli,\u00a0Qiao Yu, Dong Chao (2023) Diffbir: Towards blind image restoration with generative diffusion prior. Preprint at arXiv:2308.15070","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"11110_CR109","doi-asserted-by":"crossref","unstructured":"Lin Yuanze, Chen Yi-Wen, Tsai Yi-Hsuan,\u00a0Jiang Lu, Yang Ming-Hsuan (2023) Text-driven image editing via learnable regions. Preprint at arXiv:2311.16432","DOI":"10.1109\/CVPR52733.2024.00674"},{"key":"11110_CR110","unstructured":"Lin Zinan, Gopi Sivakanth, Kulkarni Janardhan, Nori Harsha, Yekhanin Sergey (2023) Differentially private synthetic data via foundation model apis 1: Images. Preprint at arXiv:2305.15560"},{"key":"11110_CR111","doi-asserted-by":"crossref","unstructured":"Ling Pengyang, Chen Lin, Zhang Pan, Chen Huaian,\u00a0Jin Yi, Zheng Jinjin (2024) Freedrag: Feature dragging for reliable point-based image editing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6860\u20136870","DOI":"10.1109\/CVPR52733.2024.00655"},{"issue":"4","key":"11110_CR112","first-page":"105","volume":"56","author":"Yang Ling","year":"2024","unstructured":"Ling Yang, Zhilong Zhang, Yang Song, Hong Shenda Xu, Runsheng Zhao Yue, Wentao Zhang, Bin Cui, Ming-Hsuan Yang (2024) Diffusion models: a comprehensive survey of methods and applications. ACM Comput Surv 56(4):105\u201339","journal-title":"ACM Comput Surv"},{"key":"11110_CR113","unstructured":"Liu Anji, Niepert Mathias, den Broeck Guy Van (2024) Image inpainting via tractable steering of diffusion models. In The Twelfth International Conference on Learning Representations"},{"key":"11110_CR114","doi-asserted-by":"crossref","unstructured":"Liu Haipeng, Wang Yang, Qian Biao, Wang Meng, Rui Yong (2024) Structure matters: Tackling the semantic discrepancy in diffusion models for image inpainting. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8038\u20138047","DOI":"10.1109\/CVPR52733.2024.00768"},{"key":"11110_CR115","doi-asserted-by":"crossref","unstructured":"Liu Jiawei, Wang Qiang, Fan Huijie, Wang Yinong, Tang Yandong, Qu Liangqiong (2023) Residual denoising diffusion models. Preprint at arXiv:2308.13712","DOI":"10.1109\/CVPR52733.2024.00268"},{"key":"11110_CR116","doi-asserted-by":"crossref","unstructured":"Liu Jinxiu,\u00a0Liu Qi (2024) R3CD: scene graph to image generation with relation-aware compositional contrastive control diffusion. In Thirty-Eighth AAAI Conference on Artificial Intelligence, pp 3657\u20133665","DOI":"10.1609\/aaai.v38i4.28155"},{"key":"11110_CR117","unstructured":"Liu Xian, Ren Jian, Siarohin Aliaksandr, Skorokhodov Ivan, Li Yanyu, Lin Dahua, Liu Xihui, Liu Ziwei, Tulyakov Sergey (2024) Hyperhuman: Hyper-realistic human generation with latent structural diffusion. In The Twelfth International Conference on Learning Representations"},{"key":"11110_CR118","doi-asserted-by":"crossref","unstructured":"Liu Xihui, Park Dong Huk, Azadi Samaneh, Zhang Gong, Chopikyan Arman, Yuxiao Hu, Shi Humphrey, Rohrbach Anna, Darrell Trevor (2023) More control for free! image synthesis with semantic diffusion guidance. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 289\u2013299","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"11110_CR119","unstructured":"Liu Yixin, Zhang Kai, Li Yuan, Yan Zhiling, Gao Chujie, Chen Ruoxi, Yuan Zhengqing, Huang Yue, Sun Hanchi, Gao Jianfeng, He Lifang, Sun Lichao (2024) Sora: A review on background, technology, limitations, and opportunities of large vision models. Preprint at arXiv:2402.17177"},{"key":"11110_CR120","unstructured":"Lu Cheng, Zhou Yuhao, Bao Fan, Chen Jianfei, Li Chongxuan, Zhu Jun (2022) Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models. Preprint at arXiv:2211.01095"},{"key":"11110_CR121","unstructured":"Luccioni Alexandra Sasha, Akiki Christopher, Mitchell Margaret, Jernite Yacine (2023) Stable bias: Analyzing societal representations in diffusion models. Preprint at arXiv:2303.11408"},{"key":"11110_CR122","doi-asserted-by":"crossref","unstructured":"Lugmayr Andreas, Danelljan Martin, Romero Andres, Fisher Yu, Timofte Radu, Van Gool Luc (2022) Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11461\u201311471","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"11110_CR123","unstructured":"Luo Calvin (2022) Understanding diffusion models: a unified perspective. Preprint at arXiv:2208.11970"},{"key":"11110_CR124","doi-asserted-by":"crossref","unstructured":"Luo Shitong, Wei Hu (2021) Diffusion probabilistic models for 3D point cloud generation. In IEEE Conference on Computer Vision and Pattern Recognition, pp 2837\u20132845","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"11110_CR125","unstructured":"Luo Weijian (2023) A comprehensive survey on knowledge distillation of diffusion models. Preprint at arXiv:2304.04262"},{"key":"11110_CR126","doi-asserted-by":"crossref","unstructured":"Luo Xiaotong, Xie Yuan, Yanyun Qu, Yun Fu (2024) Skipdiff: Adaptive skip diffusion model for high-fidelity perceptual image super-resolution. In Thirty-Eighth AAAI Conference on Artificial Intelligence, pp 4017\u20134025","DOI":"10.1609\/aaai.v38i5.28195"},{"key":"11110_CR127","doi-asserted-by":"crossref","unstructured":"Luo Ziwei, Gustafsson Fredrik K, Zhao Zheng, Sj\u00f6lund Jens, Sch\u00f6n Thomas B (2023) Refusion: Enabling large-size realistic image restoration with latent-space diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1680\u20131691","DOI":"10.1109\/CVPRW59228.2023.00169"},{"key":"11110_CR128","doi-asserted-by":"crossref","unstructured":"Ma Nanye, Goldstein Mark, Albergo Michael S, BoffiNicholas M, Vanden-Eijnden Eric, Xie Saining (2024) Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers. Preprint at arXiv:2401.08740","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"11110_CR129","unstructured":"Maggiora Gabriel della, Croquevielle Luis Alberto, Deshpande Nikita, Horsley Harry, Heinis Thomas, Yakimovich Artur (2024) Conditional variational diffusion models. In The Twelfth International Conference on Learning Representations"},{"key":"11110_CR130","doi-asserted-by":"crossref","unstructured":"Metzger Nando, Daudt Rodrigo Caye, Schindler Konrad (2023) Guided depth super-resolution by deep anisotropic diffusion. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18237\u201318246","DOI":"10.1109\/CVPR52729.2023.01749"},{"key":"11110_CR131","unstructured":"Midjourney. https:\/\/www.midjourney.com\/home"},{"key":"11110_CR132","unstructured":"Miyake Daiki, Iohara Akihiro,\u00a0Saito Yu, Tanaka Toshiyuki (2023) Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models. Preprint at arXiv:2305.16807"},{"issue":"1","key":"11110_CR133","doi-asserted-by":"crossref","first-page":"3","DOI":"10.3390\/jimaging9010003","volume":"9","author":"Bhandari Mohan","year":"2023","unstructured":"Mohan Bhandari, Arjun Neupane, Saurav Mallik, Loveleen Gaur, Hong Qin (2023) Auguring fake face images using dual input convolution neural network. J Imaging 9(1):3","journal-title":"J Imaging"},{"key":"11110_CR134","doi-asserted-by":"crossref","unstructured":"Mokady Ron, Hertz Amir, Aberman Kfir, Pritch Yael, Cohen-Or Daniel (2023) Null-text inversion for editing real images using guided diffusion models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6038\u20136047","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"11110_CR135","doi-asserted-by":"crossref","unstructured":"Moser Brian B, Shanbhag Arundhati S, Raue Federico, Frolov Stanislav, Palacio Sebastian, Dengel Andreas (2024) Diffusion models, image super-resolution and everything: A survey. IEEE Transactions on Neural Networks and Learning Systems, pp 1\u201321","DOI":"10.1109\/TNNLS.2024.3476671"},{"key":"#cr-split#-11110_CR136.1","unstructured":"M\u00fcller Vincent C, Bostrom Nick (2013) Future progress in artificial intelligence: A survey of expert opinion. In Vincent C. M\u00fcller,"},{"key":"#cr-split#-11110_CR136.2","unstructured":"(ed) Fundamental Issues of Artificial Intelligence - 2nd Conference on Philosophy and Theory of Artificial Intelligence, PT-AI 2013, Oxford, UK, September 21-22, 2013, selected and invited papers, vol 376 of Synthese Library, pp 555-572"},{"key":"11110_CR137","doi-asserted-by":"crossref","unstructured":"Naik Ranjita, Nushi Besmira (2023) Social biases through the text-to-image generation lens. In Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society, pp 786\u2013808","DOI":"10.1145\/3600211.3604711"},{"issue":"3","key":"11110_CR138","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1016\/j.concog.2009.04.011","volume":"18","author":"A Nash Robert","year":"2009","unstructured":"Nash Robert A, Wade Kimberley A, Brewer Rebecca J (2009) Why do doctored images distort memory? Conscious Cogn 18(3):773\u2013780","journal-title":"Conscious Cogn"},{"key":"11110_CR139","doi-asserted-by":"crossref","unstructured":"Neal Radford M (2001) Annealed importance sampling. Stat Comput 11:125\u2013139","DOI":"10.1023\/A:1008923215028"},{"issue":"5","key":"11110_CR140","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/JSTSP.2020.3007250","volume":"14","author":"C Neves Jo\u00e3o","year":"2020","unstructured":"Neves Jo\u00e3o C, Ruben Tolosana, Rub\u00e9n Vera-Rodr\u00edguez, Vasco Lopes, Hugo Proen\u00e7a, Julian Fi\u00e9rrez (2020) Ganprintr: Improved fakes and evaluation of the state of the art in face manipulation detection. IEEE J Sel Top Signal Process 14(5):1038\u20131048","journal-title":"IEEE J Sel Top Signal Process"},{"key":"11110_CR141","unstructured":"Nguyen Thao, Li Yuheng, Ojha Utkarsh, Lee Yong Jae (2023) Visual instruction inversion: Image editing via visual prompting. Preprint at arXiv:2307.14331"},{"key":"11110_CR142","doi-asserted-by":"crossref","unstructured":"Nguyen Thao, Ojha Utkarsh, Li Yuheng, Liu Haotian, Lee Yong Jae (2024) Edit one for all: Interactive batch image editing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8271\u20138280","DOI":"10.1109\/CVPR52733.2024.00790"},{"key":"11110_CR143","doi-asserted-by":"crossref","unstructured":"Ni Zixuan, Wei Longhui, Li Jiacheng, Tang Siliang, Zhuang Yueting,\u00a0Tian Qi (2023) Degeneration-tuning: Using scrambled grid shield unwanted concepts from stable diffusion. In Proceedings of the 31st ACM International Conference on Multimedia, pp 8900\u20138909","DOI":"10.1145\/3581783.3611867"},{"key":"11110_CR144","unstructured":"Nichol Alexander Quinn, Dhariwal Prafulla (2022) Improved denoising diffusion probabilistic models. In Proceedings of the 38th International Conference on Machine Learning, vol 139, pp 8162\u20138171"},{"key":"11110_CR145","doi-asserted-by":"publisher","first-page":"1494","DOI":"10.1109\/LSP.2024.3398538","volume":"31","author":"Huang Nisha","year":"2024","unstructured":"Nisha Huang, Yuxin Zhang, Weiming Dong (2024) Style-a-video: Agile diffusion for arbitrary text-based video style transfer. IEEE Signal Process Lett 31:1494\u20131498","journal-title":"IEEE Signal Process Lett"},{"key":"11110_CR146","doi-asserted-by":"crossref","unstructured":"Nunes Lucas, Marcuzzi Rodrigo, Mersch Benedikt, Behley Jens, Stachniss Cyrill (2024) Scaling diffusion models to real-world 3d lidar scene completion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 14770\u201314780","DOI":"10.1109\/CVPR52733.2024.01399"},{"key":"11110_CR147","doi-asserted-by":"crossref","unstructured":"Olaf Ronneberger, Philipp Fischer, Thomas Brox (2015) U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention vol 9351, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11110_CR148","unstructured":"OpenAI (2023) GPT-4 technical report. Preprint at arXiv:2303.08774"},{"key":"11110_CR149","unstructured":"OpenAI (2023) Video generation models as world simulators. https:\/\/openai.com\/index\/video-generation-models-as-world-simulators\/"},{"key":"11110_CR150","doi-asserted-by":"crossref","unstructured":"Pan Zhihong, Zhou Xin, Tian Hao (2023) Arbitrary style guidance for enhanced diffusion-based text-to-image generation. In IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, January 2-7, 2023, pp 4450\u20134460","DOI":"10.1109\/WACV56688.2023.00444"},{"key":"11110_CR151","doi-asserted-by":"crossref","unstructured":"Pang Lianyu, Yin Jian, Xie Haoran, Wang Qiping, Li Qing, Mao Xudong (2023) Cross initialization for personalized text-to-image generation. Preprint at arXiv:2312.15905","DOI":"10.1109\/CVPR52733.2024.00802"},{"key":"11110_CR152","doi-asserted-by":"crossref","unstructured":"Parmar Gaurav, Zhang Richard, Zhu Jun-Yan (2022) On aliased resizing and surprising subtleties in GAN evaluation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022, pp 11400\u201311410","DOI":"10.1109\/CVPR52688.2022.01112"},{"issue":"7","key":"11110_CR153","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1162\/NECO_a_00142","volume":"23","author":"Vincent Pascal","year":"2011","unstructured":"Pascal Vincent (2011) A connection between score matching and denoising autoencoders. Neural Comput 23(7):1661\u20131674","journal-title":"Neural Comput"},{"key":"11110_CR154","doi-asserted-by":"crossref","unstructured":"Patni Suraj, Agarwal Aradhye, Arora Chetan (2024) Ecodepth: Effective conditioning of diffusion models for monocular depth estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June, pp 28285\u201328295","DOI":"10.1109\/CVPR52733.2024.02672"},{"key":"11110_CR155","doi-asserted-by":"crossref","unstructured":"Peebles William, Xie Saining (2023) Scalable diffusion models with transformers. In IEEE\/CVF International Conference on Computer Vision, pp 4172\u20134182","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"11110_CR156","unstructured":"Pham Minh, Marshall Kelly O, Cohen Niv, Mittal Govind, Hegde Chinmay (2023) Circumventing concept erasure methods for text-to-image generative models. In The Twelfth International Conference on Learning Representations"},{"key":"11110_CR157","doi-asserted-by":"crossref","unstructured":"PNVR Koutilya, Singh Bharat, Ghosh Pallabi, Siddiquie Behjat, Jacobs David (2023) Ld-znet: A latent diffusion approach for text-based image segmentation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 4157\u20134168","DOI":"10.1109\/ICCV51070.2023.00384"},{"issue":"2","key":"11110_CR158","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15063","volume":"43","author":"R Po","year":"2024","unstructured":"Po R, Yifan W, Golyanik V, Aberman K, Barron JT, Bermano A, Chan E, Dekel T, Holynski A, Kanazawa A, Liu CK, Liu L, Mildenhall B, Nie\u00c3\u00ffner M, Ommer B, Theobalt C, Wonka P, Wetzstein G (2024) State of the art on diffusion models for visual computing. Comput Graph Forum 43(2):e15063","journal-title":"Comput Graph Forum"},{"key":"11110_CR159","first-page":"8780","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal, Alexander Nichol (2021) Diffusion models beat GANS on image synthesis. Adv Neural Inf Process Syst 34:8780\u20138794","journal-title":"Adv Neural Inf Process Syst"},{"key":"11110_CR160","doi-asserted-by":"crossref","unstructured":"Qi Tianhao, Fang Shancheng, Wu Yanze, Xie Hongtao, Liu Jiawei, Chen Lang, He Qian, Zhang Yongdong (2024) Deadiff: An efficient stylization diffusion model with disentangled representations. Preprint at arXiv:2403.06951","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"11110_CR161","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.patrec.2023.10.021","volume":"176","author":"Xu Qiang","year":"2023","unstructured":"Qiang Xu, Hao Wang, Laijin Meng, Zhongjie Mi, Jianye Yuan, Hong Yan (2023) Exposing fake images generated by text-to-image diffusion models. Pattern Recognit Lett 176:76\u201382","journal-title":"Pattern Recognit Lett"},{"key":"11110_CR162","doi-asserted-by":"crossref","unstructured":"Qingping Zheng, Ling Zheng, Yuanfan Guo, Ying Li, Songcen Xu, Jiankang Deng, Hang Xu (2024) Self-adaptive reality-guided diffusion for artifact-free super-resolution. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 25806\u201325816","DOI":"10.1109\/CVPR52733.2024.02438"},{"key":"11110_CR163","unstructured":"Qinsheng Zhang, Yongxin Chen (2023) Fast sampling of diffusion models with exponential integrator"},{"key":"11110_CR164","doi-asserted-by":"crossref","unstructured":"Qiu Xinmin, Han Congying, Zhang Zicheng, Li Bonan, Guo Tiande, Nie Xuecheng (2023) Diffbfr: Bootstrapping diffusion model for blind face restoration. In Proceedings of the 31st ACM International Conference on Multimedia, pp 7785\u20137795","DOI":"10.1145\/3581783.3611731"},{"key":"11110_CR165","doi-asserted-by":"crossref","unstructured":"Qu Yiting, Shen Xinyue, He Xinlei, Backes Michael, Zannettou Savvas, Zhang Yang (2023) Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, pp 3403\u20133417","DOI":"10.1145\/3576915.3616679"},{"key":"11110_CR166","unstructured":"Quinn Nichol Alexander, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, Mark Chen (2022) GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In International Conference on Machine Learning vol 162, pp 16784\u201316804"},{"key":"11110_CR167","unstructured":"Radford Alec, Kim Jong Wook, Hallacy Chris, Ramesh Aditya, Goh Gabriel, Agarwal Sandhini, Sastry Girish, Askell Amanda, Mishkin Pamela, Clark Jack, Krueger Gretchen, Sutskever Ilya (2021) Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning, vol 139, pp 8748\u20138763"},{"key":"11110_CR168","unstructured":"Ramesh Aditya, Dhariwal Prafulla, Nichol Alex, Chu Casey, Chen Mark (2022) Hierarchical text-conditional image generation with CLIP latents. Preprint at arXiv:2204.06125"},{"key":"11110_CR169","unstructured":"Ramesh Aditya, Dhariwal Prafulla, Nichol Alex, Chu Casey, Chen Mark (2022) Hierarchical text-conditional image generation with clip latents. Preprint at arXiv:2204.06125"},{"key":"11110_CR170","unstructured":"Ramesh Aditya, Pavlov Mikhail, Goh Gabriel, Gray Scott, Voss Chelsea, Radford Alec, Chen Mark, Sutskever Ilya (2021) Zero-shot text-to-image generation. In Marina Meila and Tong Zhang (eds), Proceedings of the 38th International Conference on Machine Learning, vol 139, pp 8821\u20138831"},{"key":"11110_CR171","unstructured":"Rando Javier, Paleka Daniel, Lindner David, Heim Lennart, Tram\u00e8r Florian (2022) Red-teaming the stable diffusion safety filter. Preprint at arXiv:2210.04610"},{"key":"11110_CR172","unstructured":"Reed Scott E, Akata Zeynep, Yan Xinchen, Logeswaran Lajanugen, Schiele Bernt, Lee Honglak (2016) Generative adversarial text to image synthesis. In Proceedings of the 33nd International Conference on Machine Learning, vol 48, pp 1060\u20131069"},{"key":"11110_CR173","doi-asserted-by":"crossref","unstructured":"Ren Mengwei, Delbracio Mauricio, Talebi Hossein, Gerig Guido, Milanfar Peyman (2023) Multiscale structure guided diffusion for image deblurring. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 10721\u201310733","DOI":"10.1109\/ICCV51070.2023.00984"},{"key":"11110_CR174","doi-asserted-by":"crossref","unstructured":"Rombach Robin, Blattmann Andreas, Lorenz Dominik, Esser Patrick, Ommer Bj\u00f6rn (2022) High-resolution image synthesis with latent diffusion models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10674\u201310685","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11110_CR175","doi-asserted-by":"crossref","unstructured":"Saharia Chitwan, Chan William, Saxena Saurabh, Li Lala, Whang Jay, Denton Emily L., Kamyar Seyed Ghasemipour Seyed, Lopes Raphael Gontijo, Ayan Burcu Karagol, Salimans Tim, Ho Jonathan, Fleet David J, Norouzi Mohammad (2022) Photorealistic text-to-image diffusion models with deep language understanding. In Advances in Neural Information Processing Systems","DOI":"10.1145\/3528233.3530757"},{"key":"11110_CR176","doi-asserted-by":"crossref","unstructured":"Scene generation with hierarchical latent diffusion models (2023) Seung Wook Kim, Bradley Brown, Kangxue Yin, Karsten Kreis, Katja Schwarz, Daiqing Li, Robin Rombach, Antonio Torralba, and Sanja Fidler. Neuralfield-ldm. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8496\u20138506","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"11110_CR177","doi-asserted-by":"crossref","unstructured":"Schramowski Patrick, Brack Manuel, Deiseroth Bjorn, Kersting Kristian (2023) Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 22522\u201322531","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"11110_CR178","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105138","volume":"148","author":"Lee Seung-Lee","year":"2024","unstructured":"Seung-Lee Lee, Minjae Kang, Jong-Uk Hou (2024) Localization of diffusion model-based inpainting through the inter-intra similarity of frequency features. Image Vis Comput 148:105138","journal-title":"Image Vis Comput"},{"key":"11110_CR179","doi-asserted-by":"crossref","unstructured":"Shang Kai, Shao Mingwen, Wang Chao, Cheng Yuanshuo, Wang Shuigen (2024) Multi-domain multi-scale diffusion model for low-light image enhancement. In Thirty-Eighth AAAI Conference on Artificial Intelligence, pp 4722\u20134730","DOI":"10.1609\/aaai.v38i5.28273"},{"key":"11110_CR180","unstructured":"Shen Xudong, Du Chao, Pang Tianyu, Lin Min, Wong Yongkang, Kankanhalli Mohan (2023) Finetuning text-to-image diffusion models for fairness. Preprint at arXiv:2311.07604"},{"issue":"2","key":"11110_CR181","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1177\/1461444818799526","volume":"21","author":"Cuihua Shen","year":"2019","unstructured":"Shen Cuihua, Kasra Mona, Pan Wenjing, Bassett Grace A, Malloch Yining, O\u2019Brien James F (2019) Fake images: The effects of source, intermediary, and digital media literacy on contextual assessment of image credibility online. New Media Soc 21(2):438\u2013463. https:\/\/doi.org\/10.1177\/1461444818799526","journal-title":"New Media Soc"},{"key":"11110_CR182","unstructured":"Sohl-Dickstein Jascha, Weiss Eric A, Maheswaranathan Niru, Ganguli Surya (2015) Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, vol 37, pp 2256\u20132265"},{"key":"11110_CR183","unstructured":"Song Yang, Ermon Stefano (2019) Generative modeling by estimating gradients of the data distribution. Adv Neural Inform Process Syst 32"},{"key":"11110_CR184","unstructured":"Song Yang, Garg Sahaj, Shi Jiaxin, Ermon Stefano (2020) Sliced score matching: A scalable approach to density and score estimation. In Uncertainty in Artificial Intelligence, pp 574\u2013584"},{"key":"11110_CR185","unstructured":"Song Yang, Sohl-Dickstein Jascha, Kingma Diederik P, Kumar Abhishek, Ermon Stefano, Poole Ben (2020) Score-based generative modeling through stochastic differential equations. Preprint at arXiv:2011.13456,"},{"key":"11110_CR186","doi-asserted-by":"crossref","unstructured":"Structured prediction for efficient text-to-image generation (2024) Jayasumana, Daniel Glasner, Srikumar Ramalingam, Andreas Veit, Ayan Chakrabarti, and Sanjiv Kumar. Markovgen. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9316\u20139325","DOI":"10.1109\/CVPR52733.2024.00890"},{"key":"11110_CR187","unstructured":"Suttisak Wizadwongsa, Supasorn Suwajanakorn (2023) Accelerating guided diffusion sampling with splitting numerical methods"},{"key":"11110_CR188","doi-asserted-by":"crossref","unstructured":"Tao Xu, Zhang Pengchuan, Huang Qiuyuan, Zhang Han, Gan Zhe, Huang Xiaolei, He Xiaodong (2018) Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In IEEE Conference on Computer Vision and Pattern Recognition, pp 1316\u20131324","DOI":"10.1109\/CVPR.2018.00143"},{"key":"11110_CR189","unstructured":"Tim Salimans, Jonathan Ho (2022) Progressive distillation for fast sampling of diffusion models"},{"key":"11110_CR190","unstructured":"Ulhaq Anwaar, Akhtar Naveed, Pogrebna Ganna (2022) Efficient diffusion models for vision: a survey. Preprint at arXiv:2210.09292"},{"key":"11110_CR191","unstructured":"Vahdat Arash, Kreis Karsten, Kautz Jan (2021) Score-based generative modeling in latent space. In Advances in Neural Information Processing Systems, pp 11287\u201311302"},{"key":"11110_CR192","unstructured":"van den Oord A\u00e4ron, Vinyals Oriol, Kavukcuoglu Koray (2017) Neural discrete representation learning. In Advances in Neural Information Processing Systems, pp 6306\u20136315"},{"key":"11110_CR193","unstructured":"Wang Hanzhang, Wang Haoran, Yang Jinze, Yu Zhongrui, Xie Zeke, Tian Lei, Xiao Xinyan, Jiang Junjun, Liu Xianming, Sun Mingming (2024) Hicast: Highly customized arbitrary style transfer with adapter enhanced diffusion models. Preprint at arXiv:2401.05870"},{"key":"11110_CR194","unstructured":"Wang Haonan, Shen Qianli, Tong Yao, Zhang Yang, Kawaguchi Kenji (2024) The stronger the diffusion model, the easier the backdoor: Data poisoning to induce copyright breaches without adjusting finetuning pipeline. Preprint at arXiv:2401.04136"},{"key":"11110_CR195","unstructured":"Wang Liyan, Yang Qinyu, Wang Cong, Wang Wei, Pan Jinshan, Su Zhixun (2023) Learning a coarse-to-fine diffusion transformer for image restoration. Preprint at arXiv:2308.08730"},{"key":"11110_CR196","unstructured":"Wang Qian, Zhang Biao, Birsak Michael, Wonka Peter (2023) Mdp: A generalized framework for text-guided image editing by manipulating the diffusion path. Preprint at arXiv:2303.16765"},{"key":"11110_CR197","doi-asserted-by":"crossref","unstructured":"Wang Yibin, Zhang Weizhong, Zheng Jianwei, Jin Cheng (2023) High-fidelity person-centric subject-to-image synthesis. Preprint at arXiv:2311.10329","DOI":"10.1109\/CVPR52733.2024.00733"},{"key":"11110_CR198","doi-asserted-by":"crossref","unstructured":"Wang Yufei, Yang Wenhan, Chen Xinyuan, Wang Yaohui, Guo Lanqing, Chau Lap-Pui, Ziwei Liu Yu, Qiao Alex C, Kot, and Bihan Wen. (2024) Sinsr: Diffusion-based image super-resolution in a single step. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 25796\u201325805","DOI":"10.1109\/CVPR52733.2024.02437"},{"key":"11110_CR199","doi-asserted-by":"crossref","unstructured":"Wang Zhicai, Wei Longhui, Wang Tan, Chen Heyu, Hao Yanbin, Wang Xiang, He Xiangnan, Tian Qi (2024) Enhance image classification via inter-class image mixup with diffusion model. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 17223\u201317233","DOI":"10.1109\/CVPR52733.2024.01630"},{"key":"11110_CR200","doi-asserted-by":"crossref","unstructured":"Wang Zhizhong, Zhao Lei, Xing Wei (2023) Stylediffusion: Controllable disentangled style transfer via diffusion models. In IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1\u20136, 2023, pp 7643\u20137655","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"11110_CR201","doi-asserted-by":"crossref","unstructured":"Wang Zhizhong, Zhao Lei, Xing Wei (2023) Stylediffusion: Controllable disentangled style transfer via diffusion models. In IEEE\/CVF International Conference on Computer Vision, pp 7643\u20137655","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"11110_CR202","doi-asserted-by":"crossref","unstructured":"Weng Zhenzhen, S\u00e1nchez Laura Bravo, Yeung-Levy Serena (2024) Diffusion-hpc: Synthetic data generation for human mesh recovery in challenging domains. In International Conference on 3D Vision, pp 257\u2013267","DOI":"10.1109\/3DV62453.2024.00043"},{"key":"11110_CR203","unstructured":"Wenliang Zhao, Lujia Bai, Yongming Rao, Jie Zhou, Jiwen Lu (2023) Unipc: A unified predictor-corrector framework for fast sampling of diffusion models. In Advances in Neural Information Processing Systems"},{"key":"11110_CR204","doi-asserted-by":"crossref","unstructured":"Xia Bin, Zhang Yulun, Wang Shiyin, Wang Yitong, Xinglong Wu, Tian Yapeng, Yang Wenming, Van Gool Luc (2023) Diffir: Efficient diffusion model for image restoration. In IEEE\/CVF International Conference on Computer Vision, pp 13049\u201313059","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"11110_CR205","doi-asserted-by":"crossref","unstructured":"Xing Zhen, Feng Qijun, Chen Haoran,\u00a0Dai Qi, Hu Han, Xu Hang, Wu Zuxuan, Jiang Yu-Gang (2024) A survey on video diffusion models. ACM Comput Surv 57(2)","DOI":"10.1145\/3696415"},{"key":"11110_CR206","doi-asserted-by":"crossref","unstructured":"Xu Juncong, Yang Yang, Fang Han, Liu Honggu, Zhang Weiming (2024) Famsec: A few-shot-sample-based general ai-generated image detection method. Preprint at arXiv:2410.13156","DOI":"10.1109\/LSP.2024.3511421"},{"key":"11110_CR207","unstructured":"Xu Yilun, Deng Mingyang, Cheng Xiang, Tian Yonglong, Liu Ziming, Jaakkola Tommi S (2023) Restart sampling for improving generative processes. In Advances in Neural Information Processing Systems"},{"key":"11110_CR208","doi-asserted-by":"crossref","unstructured":"Xun Huang, Belongie Serge J (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In IEEE International Conference on Computer Vision, pp 1510\u20131519","DOI":"10.1109\/ICCV.2017.167"},{"key":"11110_CR209","unstructured":"Xunpeng Huang, Difan Zou, Hanze Dong, Yi-An Ma, Tong Zhang (2024) Faster sampling without isoperimetry via diffusion-based Monte Carlo. In The Thirty Seventh Annual Conference on Learning Theory 247:2438\u20132493"},{"key":"11110_CR210","doi-asserted-by":"crossref","unstructured":"Yang Binbin,\u00a0Luo Yi, Chen Ziliang, Wang Guangrun, Liang Xiaodan, Lin Liang (2023) Law-diffusion: Complex scene generation by diffusion with layouts. In IEEE\/CVF International Conference on Computer Vision, pp 22612\u201322622","DOI":"10.1109\/ICCV51070.2023.02072"},{"key":"11110_CR211","doi-asserted-by":"crossref","unstructured":"Yang Jingyuan, Feng Jiawei, Huang Hui (2024) Emogen: Emotional image content generation with text-to-image diffusion models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6358\u20136368","DOI":"10.1109\/CVPR52733.2024.00608"},{"key":"11110_CR212","doi-asserted-by":"crossref","unstructured":"Yang Serin, Hwang Hyunmin, Ye Jong Chul (2023) Zero-shot contrastive loss for text-guided diffusion image style transfer. In IEEE\/CVF International Conference on Computer Vision, pp 22816\u201322825","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"11110_CR213","first-page":"12438","volume":"33","author":"Song Yang","year":"2020","unstructured":"Yang Song, Stefano Ermon (2020) Improved techniques for training score-based generative models. Adv Neural Inf Process Syst 33:12438\u201312448","journal-title":"Adv Neural Inf Process Syst"},{"key":"11110_CR214","first-page":"1415","volume":"34","author":"Song Yang","year":"2021","unstructured":"Yang Song, Conor Durkan, Iain Murray, Stefano Ermon (2021) Maximum likelihood training of score-based diffusion models. Adv Neural Inf Process Syst 34:1415\u20131428","journal-title":"Adv Neural Inf Process Syst"},{"issue":"7553","key":"11110_CR215","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, Hinton Geoffrey E (2015) Deep learning. Nat 521(7553):436\u2013444","journal-title":"Nat"},{"key":"11110_CR216","unstructured":"Yarom Michal, Bitton Yonatan, Changpinyo Soravit, Aharoni Roee, Herzig Jonathan, Lang Oran, Ofek Eran, Szpektor Idan (2023) What you see is what you read? improving text-image alignment evaluation. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10-16, 2023"},{"key":"11110_CR217","doi-asserted-by":"crossref","unstructured":"Yeh Yu-Ying, Huang Jia-Bin, Kim Changil, Xiao Lei, Nguyen-Phuoc Thu, Khan Numair, Zhang Cheng, Chandraker Manmohan, Marshall Carl S, Dong Zhao, Li Zhengqin (2024) Texturedreamer: Image-guided texture synthesis through geometry-aware diffusion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4304\u20134314","DOI":"10.1109\/CVPR52733.2024.00412"},{"key":"11110_CR218","doi-asserted-by":"crossref","unstructured":"Yi Xunpeng, Han Xu, Zhang Hao, Tang Linfeng, Ma Jiayi (2023) Diff-retinex: Rethinking low-light image enhancement with A generative diffusion model. In IEEE\/CVF International Conference on Computer Vision, pp 12268\u201312277","DOI":"10.1109\/ICCV51070.2023.01130"},{"key":"11110_CR219","unstructured":"Yilun Xu, Ziming Liu, Yonglong Tian, Shangyuan Tong, Max Tegmark, Jaakkola Tommi S (2023) PFGM++: unlocking the potential of physics-inspired generative models. In International Conference on Machine Learning vol 202, pp 38566\u201338591"},{"key":"11110_CR220","unstructured":"Yiyang Ma, Huan Yang, Yang Wenhan Fu, Jianlong Liu Jiaying (2024) Solving diffusion odes with optimal boundary conditions for better image super-resolution"},{"issue":"7","key":"11110_CR221","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/3448250","volume":"64","author":"Bengio Yoshua","year":"2021","unstructured":"Yoshua Bengio, Yann LeCun, Hinton Geoffrey E (2021) Deep learning for AI. Commun ACM 64(7):58\u201365","journal-title":"Commun ACM"},{"key":"11110_CR222","unstructured":"Yu Jiahui Xu, Yuanzhong Koh Jing, Yu Luong Thang, Gunjan Baid, Zirui Wang, Vasudevan Vijay Ku, Alexander Yang Yinfei, Karagol Ayan Burcu, Ben Hutchinson, Wei Han, Zarana Parekh, Xin Li, Han Zhang, Baldridge Jason Wu, Yonghui, (2022) Scaling autoregressive models for content-rich text-to-image generation. Trans Mach Learn Res 2022"},{"issue":"2","key":"11110_CR223","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2024.100082","volume":"2","author":"Fan Yuheng","year":"2024","unstructured":"Yuheng Fan, Hanxi Liao, Shiqi Huang, Yimin Luo, Huazhu Fu, Haikun Qi (2024) A survey of emerging applications of diffusion probabilistic models in MRI. Meta-Radiol 2(2):100082","journal-title":"Meta-Radiol"},{"key":"11110_CR224","doi-asserted-by":"crossref","unstructured":"Zeng Haijin, Cao Jiezhang, Zhang Kai, Chen Yongyong, Luong Hiep, Philips Wilfried (2024) Unmixing diffusion for self-supervised hyperspectral image denoising. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 27820\u201327830","DOI":"10.1109\/CVPR52733.2024.02628"},{"key":"11110_CR225","unstructured":"Zhang Chenshuang, Zhang Chaoning, Zhang Mengchun, Kweon In So (2023) Text-to-image diffusion models in generative AI: A survey. Preprint at arXiv:2303.07909"},{"key":"11110_CR226","unstructured":"Zhang Chenshuang, Zhang Chaoning, Zhang Mengchun, Kweon In So (2023) Text-to-image diffusion models in generative AI: A survey. Preprint at arXiv:2303.07909"},{"key":"11110_CR227","unstructured":"Zhang Chenshuang, Zhang Chaoning, Zheng Sheng, Zhang Mengchun, Qamar Maryam, Bae Sung-Ho, Kweon In So (2023) A survey on audio diffusion models: Text to speech synthesis and enhancement in generative AI. Preprint at arXiv:2303.13336"},{"key":"11110_CR228","doi-asserted-by":"crossref","unstructured":"Zhang Eric, Wang Kai, Xu Xingqian, Wang Zhangyang, Shi Humphrey (2023) Forget-me-not: Learning to forget in text-to-image diffusion models. Preprint at arXiv:2303.17591","DOI":"10.1109\/CVPRW63382.2024.00182"},{"key":"11110_CR229","doi-asserted-by":"crossref","unstructured":"Zhang Han, Xu Tao, Li Hongsheng (2017) Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In IEEE International Conference on Computer Vision, pp 5908\u20135916","DOI":"10.1109\/ICCV.2017.629"},{"key":"11110_CR230","unstructured":"Zhang Jie, Kerschbaum Florian, Zhang Tianwei, et al (2023) Backdooring textual inversion for concept censorship. Preprint at arXiv:2308.10718"},{"key":"11110_CR231","doi-asserted-by":"crossref","unstructured":"Zhang Kaiwen, Zhou Yifan, Xudong Xu, Dai Bo, Pan Xingang (2024) Diffmorpher: Unleashing the capability of diffusion models for image morphing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7912\u20137921","DOI":"10.1109\/CVPR52733.2024.00756"},{"key":"11110_CR232","doi-asserted-by":"crossref","unstructured":"Zhang Xinyi, Li Naiqi, Li Jiawei, Dai Tao, Jiang Yong, Xia Shu-Tao (2023) Unsupervised surface anomaly detection with diffusion probabilistic model. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 6782\u20136791","DOI":"10.1109\/ICCV51070.2023.00624"},{"key":"11110_CR233","unstructured":"Zhang Yang, Tzun Teoh Tze, Hern Lim Wei, Wang Haonan, Kawaguchi Kenji (2023) Investigating copyright issues of diffusion models under practical scenarios. Preprint at arXiv:2311.12803"},{"key":"11110_CR234","doi-asserted-by":"crossref","unstructured":"Zhang Yimeng, Jia Jinghan, Chen Xin, Chen Aochuan, Zhang Yihua, Liu Jiancheng,\u00a0Ding Ke, Liu Sijia (2023) To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images... for now. Preprint at arXiv:2310.11868","DOI":"10.1007\/978-3-031-72998-0_22"},{"key":"11110_CR235","doi-asserted-by":"crossref","unstructured":"Zhang Yuxin, Huang Nisha, Tang Fan, Huang Haibin, Ma Chongyang, Dong Weiming, Xu Changsheng (2023) Inversion-based style transfer with diffusion models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023, pp 10146\u201310156","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"11110_CR236","doi-asserted-by":"crossref","unstructured":"Zhao Kai, Hung Alex Ling Yu, Pang Kaifeng, Zheng Haoxin, Sung Kyunghyun (2023) Partdiff: Image super-resolution with partial diffusion models. Preprint at arXiv:2307.11926","DOI":"10.1109\/TMI.2024.3483109"},{"key":"11110_CR237","doi-asserted-by":"crossref","unstructured":"Zhao Pancheng, Peng Xu, Qin Pengda, Fan Deng-Ping, Zhang Zhicheng, Jia Guoli, Zhou Bowen, Yang Jufeng (2024) Lake-red: Camouflaged images generation by latent background knowledge retrieval-augmented diffusion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4092\u20134101","DOI":"10.1109\/CVPR52733.2024.00392"},{"key":"11110_CR238","unstructured":"Zhaoyang Lyu, Kong Zhifeng Xu, Xudong Pan Liang, Dahua Lin (2022) A conditional point diffusion-refinement paradigm for 3D point cloud completion"},{"key":"11110_CR239","doi-asserted-by":"crossref","unstructured":"Zheng Sizhe, Gao Pan, Zhou Peng, Qin Jie (2024) Puff-net: Efficient style transfer with pure content and style feature fusion network. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8059\u20138068","DOI":"10.1109\/CVPR52733.2024.00770"},{"key":"11110_CR240","doi-asserted-by":"crossref","unstructured":"Zhou Jinxin, Ding Tianyu, Chen Tianyi, Jiang Jiachen, Zharkov Ilya, Zhu Zhihui, Liang Luming (2023) Dream: Diffusion rectification and estimation-adaptive models. Preprint at arXiv:2312.00210","DOI":"10.1109\/CVPR52733.2024.00797"},{"key":"11110_CR241","doi-asserted-by":"crossref","unstructured":"Zhou Tianhao, Li Haipeng, Wang Ziyi,\u00a0Luo Ao, Zhang Chen-Lin, Li Jiajun, Zeng Bing, Liu Shuaicheng (2024) Recdiffusion: Rectangling for image stitching with diffusion models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June, p 2692\u20132701","DOI":"10.1109\/CVPR52733.2024.00260"},{"key":"11110_CR242","unstructured":"Zhu Derui, Chen Dingfan, Grossklags Jens, Fritz Mario (2023) Data forensics in diffusion models: A systematic analysis of membership privacy. Preprint at arXiv:2302.07801"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11110-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-025-11110-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11110-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T05:40:34Z","timestamp":1740116434000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-025-11110-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,25]]},"references-count":243,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["11110"],"URL":"https:\/\/doi.org\/10.1007\/s10462-025-11110-3","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,25]]},"assertion":[{"value":"7 January 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"99"}}