{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:10:48Z","timestamp":1782483048007,"version":"3.54.5"},"reference-count":332,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JSGG20220831105002004"],"award-info":[{"award-number":["JSGG20220831105002004"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tpami.2025.3541625","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T18:40:04Z","timestamp":1739472004000},"page":"4409-4437","source":"Crossref","is-referenced-by-count":98,"title":["Diffusion Model-Based Image Editing: A Survey"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8443-6877","authenticated-orcid":false,"given":"Yi","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2826-9231","authenticated-orcid":false,"given":"Jiancheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0187-8544","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4820-0704","authenticated-orcid":false,"given":"Mingfu","family":"Yan","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2110-3554","authenticated-orcid":false,"given":"Jiaxi","family":"Lv","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-9382","authenticated-orcid":false,"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7036-6820","authenticated-orcid":false,"given":"He","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Inc, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangliang","family":"Cao","sequence":"additional","affiliation":[{"name":"Apple Inc, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0677-7358","authenticated-orcid":false,"given":"Shifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref2","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Van Den"},{"key":"ref3","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref4","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Van Den"},{"key":"ref5","first-page":"2338","article-title":"Masked autoregressive flow for density estimation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Papamakarios"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref7","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref8","article-title":"Energy-based generative adversarial network","author":"Zhao","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref10","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref12","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref15","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref17","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref18","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"issue":"4","key":"ref19","first-page":"695","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref21","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref22","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref23","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102846"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref26","article-title":"Diffusion models for image restoration and enhancement\u2013a comprehensive survey","author":"Li","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3476671"},{"key":"ref28","article-title":"DiVAE: Photorealistic images synthesis with denoising diffusion decoder","author":"Shi","year":"2022"},{"key":"ref29","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref32","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Workshop Deep Generative Models Downstream Appl.","author":"Ho"},{"key":"ref33","article-title":"Conditional image generation with score-based diffusion models","author":"Batzolis","year":"2021"},{"key":"ref34","article-title":"Analytic-DPM: An analytic estimate of the optimal reverse variance in diffusion probabilistic models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"issue":"1","key":"ref35","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref38","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref39","article-title":"Text-guided synthesis of artistic images with retrieval-augmented diffusion models","author":"Rombach","year":"2022"},{"key":"ref40","article-title":"Cold diffusion: Inverting arbitrary image transforms without noise","author":"Bansal","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00983"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3238179"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28746"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01350"},{"key":"ref50","first-page":"23045","article-title":"Image restoration with mean-reverting stochastic differential equations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01204"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref53","first-page":"23593","article-title":"Denoising diffusion restoration models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kawar"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3359769"},{"key":"ref55","article-title":"Zero-shot image restoration using denoising diffusion null-space model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3432651\/mm1"},{"key":"ref57","first-page":"25683","article-title":"Improving diffusion models for inverse problems using manifold constraints","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chung"},{"key":"ref58","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chung"},{"key":"ref59","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2022"},{"key":"ref60","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer"},{"key":"ref61","article-title":"ImaGen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref64","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.73"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref67","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023"},{"key":"ref68","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref69","article-title":"VideoGen: A reference-guided latent diffusion approach for high definition text-to-video generation","author":"Li","year":"2023"},{"key":"ref70","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00150"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref75","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3361474\/mm1"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref80","article-title":"Efficient diffusion models for vision: A survey","author":"Ulhaq","year":"2022"},{"key":"ref81","article-title":"Text-to-image diffusion model in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref82","article-title":"A survey of diffusion based image generation models: Issues and their solutions","author":"Zhang","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15063"},{"key":"ref84","article-title":"A comprehensive survey on generative diffusion models for structured data","author":"Koo","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"ref86","article-title":"SDEdit: Image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref88","article-title":"Denoising likelihood score matching for conditional score-based data generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chao"},{"key":"ref89","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karras"},{"key":"ref90","first-page":"5775","article-title":"DPM-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref91","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref93","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref94","article-title":"PixArt-$\\alpha$\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref95","article-title":"EMU: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023"},{"key":"ref96","article-title":"StyleDrop: Text-to-image generation in any style","author":"Sohn","year":"2023"},{"key":"ref97","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref103","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","author":"Zhao","year":"2023"},{"key":"ref104","article-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023"},{"key":"ref105","first-page":"13753","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00829"},{"key":"ref108","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref110","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gu,","year":"2024"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref114","first-page":"37491","article-title":"Is this loss informative? Faster text-to-image customization by tracking objective dynamics","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Voronov"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref116","first-page":"21548","article-title":"Cones: Concept neurons in diffusion models for customized generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref117","article-title":"Subject-driven text-to-image generation via apprenticeship learning","author":"Chen","year":"2023"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00816"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref120","article-title":"Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation","author":"Chen","year":"2023"},{"key":"ref121","article-title":"Photoswap: Personalized subject swapping in images","author":"Gu","year":"2023"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681396"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01371"},{"key":"ref124","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"ref126","first-page":"15869","article-title":"DifSketcher: Text guided vector sketch synthesis through latent diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xing"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00423"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2023.3290149"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00169"},{"key":"ref131","article-title":"Hierarchical integration diffusion model for realistic image deblurring","author":"Chen","year":"2023"},{"key":"ref132","first-page":"478","article-title":"Wavelet score-based generative modeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Guth"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7025-4_6"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02444"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref138","article-title":"Pseudoinverse-guided diffusion models for inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aaf14a"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25372"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3368612"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02305-2"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00787"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01057"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"ref148","article-title":"Warpdiffusion: Efficient diffusion model for high-fidelity virtual try-on","author":"Li","year":"2023"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00447"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612137"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00781"},{"key":"ref152","article-title":"MMTryon: Multi-modal multi-reference control for high-quality fashion generation","author":"Zhang","year":"2024"},{"key":"ref153","article-title":"CatVTON: Concatenation is all you need for virtual try-on with diffusion models","author":"Chong","year":"2024"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref155","article-title":"Diffusion models already have a semantic latent space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kwon"},{"key":"ref156","article-title":"Towards real-time text-driven image manipulation with unconditional diffusion models","author":"Starodubcev","year":"2023"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342645"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref159","article-title":"UNIT-DDPM: Unpaired image translation with denoising diffusion probabilistic models","author":"Sasaki","year":"2021"},{"key":"ref160","first-page":"10359","article-title":"CycleNet: Rethinking cycle consistency in text-guided diffusion for image manipulation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00529"},{"key":"ref163","article-title":"EGSDE: Unpaired image-to-image translation via energy-guided stochastic differential equations","author":"Zhao","year":"2022"},{"key":"ref164","article-title":"Fine-grained image editing by pixel-wise guidance using diffusion models","author":"Matsunaga","year":"2022"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref166","article-title":"Reference-based image composition with sketch via structure-aware diffusion model","author":"Kim","year":"2023"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448510"},{"key":"ref169","article-title":"DreamInpainter: Text-guided subject-driven image inpainting with diffusion models","author":"Xie","year":"2023"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00630"},{"key":"ref171","article-title":"Face aging via diffusion-based editing","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chen"},{"key":"ref172","article-title":"Pair-diffusion: Object-level image editing with structure-and-appearance paired diffusion models","author":"Goel","year":"2023"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00515"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00621"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612200"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref180","article-title":"MoEController: Instruction-based arbitrary image manipulation with mixture-of-expert controllers","author":"Li","year":"2023"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00667"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.646"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01208"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00847"},{"key":"ref185","article-title":"DialogPaint: A dialog-based image editing model","author":"Wei","year":"2023"},{"key":"ref186","article-title":"Inst-inpaint: Instructing to remove objects with diffusion models","author":"Yildirim","year":"2023"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00862"},{"key":"ref188","article-title":"ImageBrush: Learning visual in-context instructions for exemplar-based image manipulation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yasheng"},{"key":"ref189","article-title":"Instructany2pix: Flexible visual editing via multimodal instruction following","author":"Li","year":"2023"},{"key":"ref190","article-title":"Guiding instruction-based image editing via multimodal large language models","author":"Fu","year":"2023"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00799"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00738"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00674"},{"key":"ref194","article-title":"ChatFace: Chat-guided real face editing via diffusion latent space manipulation","author":"Yue","year":"2023"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref196","article-title":"Custom-edit: Text-guided image editing with customized diffusion models","author":"Choi","year":"2023"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8429-9_14"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref199","first-page":"26291","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref202","article-title":"Stylediffusion: Prompt-embedding inversion for text-based editing","author":"Li","year":"2023"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref204","article-title":"DragonDiffusion: Enabling drag-style manipulation on diffusion models","author":"Mou","year":"2023"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00844"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"ref207","article-title":"Diffusion-based image translation using disentangled style and content representation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kwon"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00878"},{"key":"ref209","article-title":"MagicRemover: Tuning-free text-guided image inpainting with diffusion models","author":"Yang","year":"2023"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626172"},{"key":"ref212","article-title":"Forgedit: Text guided image editing via learning and forgetting","author":"Zhang","year":"2023"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref214","article-title":"Preditor: Text guided image editing with diffusion prior","author":"Ravi","year":"2023"},{"key":"ref215","article-title":"Regeneration learning of diffusion models with rich prompts for zero-shot image translation","author":"Lin","year":"2023"},{"key":"ref216","article-title":"User-friendly image editing with minimal text input: Leveraging captioning and injection techniques","author":"Kim","year":"2023"},{"key":"ref217","article-title":"Instructedit: Improving automatic masks for diffusion-based image editing with user instructions","author":"Wang","year":"2023"},{"key":"ref218","article-title":"Direct inversion: Optimization-free text-driven real image editing with diffusion models","author":"Elarabawy","year":"2022"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01185"},{"key":"ref220","article-title":"The blessing of randomness: SDE beats ODE in general diffusion-based image editing","author":"Nie","year":"2023"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00846"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/ICICML60161.2023.10424833"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00792"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00207"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00424"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612588"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02158"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01458"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00507"},{"key":"ref231","article-title":"Fixed-point inversion for text-to-image diffusion models","author":"Meiri","year":"2023"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27931"},{"key":"ref233","article-title":"Diffusion brush: A latent diffusion model-based editing tool for AI-generated images","author":"Gholami","year":"2023"},{"key":"ref234","article-title":"Diffusion self-guidance for controllable image generation","author":"Epstein","year":"2023"},{"key":"ref235","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hertz"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref240","article-title":"Conditional score guidance for text-driven image-to-image translation","author":"Lee","year":"2023"},{"key":"ref241","article-title":"Energy-based cross attention for Bayesian context update in text-to-image diffusion models","author":"Park","year":"2023"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00415"},{"key":"ref243","article-title":"HD-Painter: High-resolution and prompt-faithful text-guided image inpainting with diffusion models","author":"Manukyan","year":"2023"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29599"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106777"},{"key":"ref247","article-title":"DifEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Couairon"},{"key":"ref248","article-title":"Region-aware diffusion for zero-shot text-driven image editing","author":"Huang","year":"2023"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00473"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70040"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_7"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00598"},{"key":"ref254","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023"},{"key":"ref255","article-title":"The stable artist: Steering semantics in diffusion latent space","author":"Brack","year":"2022"},{"key":"ref256","article-title":"SEGA: Instructing diffusion using semantic dimensions","author":"Brack","year":"2023"},{"key":"ref257","article-title":"LEDITS: Real image editing with DDPM inversion and semantic guidance","author":"Tsaban","year":"2023"},{"key":"ref258","article-title":"Object-aware inversion and reassembly for image editing","author":"Yang","year":"2023"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"ref262","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref264","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"ref265","article-title":"Wikiart dataset"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref268","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref271","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref273","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref274","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref275","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","author":"Zhang","year":"2023"},{"key":"ref276","article-title":"LLama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.24"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref280","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01390"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref284","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref285","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref287","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref289","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref290","article-title":"SUD$^{2}$2: Supervision by denoising diffusion models for image reconstruction","author":"Chan","year":"2023"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3299789"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103928"},{"key":"ref294","article-title":"Pseudoinverse-guided diffusion models for inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00958"},{"key":"ref296","first-page":"41164","article-title":"Towards coherent image inpainting using denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref297","article-title":"Diracdiffusion: Denoising and incremental reconstruction with assured data-consistency","author":"Fabian","year":"2023"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00535"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref301","article-title":"Editval: Benchmarking diffusion based text-guided image editing methods","author":"Basu","year":"2023"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"3","key":"ref303","article-title":"Improving image generation with better captions","volume-title":"Comput. Sci.","volume":"2","author":"Betker","year":"2023"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref307","first-page":"41914","article-title":"One-step diffusion distillation via deep equilibrium models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Geng"},{"key":"ref308","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref309","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_13"},{"key":"ref311","first-page":"20662","article-title":"SnapFusion: Text-to-image diffusion model on mobile devices within two seconds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref312","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00617"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459872"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01225"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02070"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00809"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991013340345203412"},{"key":"ref320","article-title":"Lasagna: Layered score distillation for disentangled object relighting","author":"Bashkirova","year":"2023"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00894"},{"key":"ref323","article-title":"Neural gaffer: Relighting any object via diffusion","author":"Jin","year":"2024"},{"key":"ref324","article-title":"Retinex-diffusion: On controlling illumination conditions in diffusion models via retinex theory","author":"Xing","year":"2024"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00226"},{"key":"ref326","article-title":"High-resolution image editing via multi-stage blended diffusion","author":"Ackermann","year":"2022"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref328","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref329","article-title":"Demystifying MMD GANs","author":"Bi\u0144kowski","year":"2018"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref331","article-title":"DreamSim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023"},{"key":"ref332","first-page":"40853","article-title":"Are these the same apple? Comparing images based on object intrinsics","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kotar"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10990047\/10884879.pdf?arnumber=10884879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:25:48Z","timestamp":1746678348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10884879\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":332,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3541625","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}