{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:08:04Z","timestamp":1742969284203,"version":"3.40.3"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732195"},{"type":"electronic","value":"9783031732201"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73220-1_2","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:02:26Z","timestamp":1730577746000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Chains of\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"given":"Yanheng","family":"Wei","sequence":"first","affiliation":[]},{"given":"Lianghua","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zhi-Fan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Mingda","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Shuailei","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"2_CR1","unstructured":"Stoked Reality XL. https:\/\/civitai.com\/models\/146039\/stoked-reality-xl?modelVersionId=162531. Accessed 24 Sept 2023"},{"key":"2_CR2","unstructured":"Aghajanyan, A., et al.: CM3: a causal masked multimodal model of the internet. arXiv preprint arXiv:2201.07520 (2022)"},{"key":"2_CR3","unstructured":"Byeon, M., Park, B., Kim, H., Lee, S., Baek, W., Kim, S.: COYO-700M: image-text pair dataset (2022). https:\/\/github.com\/kakaobrain\/coyo-dataset"},{"key":"2_CR4","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12m: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, G., Jin, C., Liu, S., Li, T.: SSD-GAN: measuring the realness in the spatial and spectral domains. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16196"},{"key":"2_CR7","unstructured":"Cheng, J., Liang, X., Shi, X., He, T., Xiao, T., Li, M.: Layoutdiffuse: adapting foundational diffusion models for layout-to-image generation (2023)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"2_CR9","unstructured":"Dong, R., et al.: Dreamllm: synergistic multimodal comprehension and creation. arXiv preprint arXiv:2309.11499 (2023)"},{"key":"2_CR10","unstructured":"Gadre, S.Y., et al.: Datacomp: in search of the next generation of multimodal datasets. arXiv preprint arXiv:2304.14108 (2023)"},{"key":"2_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Hoe, J.T., Jiang, X., Chan, C.S., Tan, Y.P., Hu, W.: Interactdiffusion: interaction control in text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"2_CR13","unstructured":"H\u00f6ppe, T., Mehrjou, A., Bauer, S., Nielsen, D., Dittadi, A.: Diffusion models for video prediction and infilling. arXiv preprint arXiv:2206.07696 (2022)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hu, H., et al.: Instruct-imagen: image generation with multi-modal instruction (2024)","DOI":"10.1109\/CVPR52733.2024.00455"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Learning disentangled identifiers for action-customized text-to-image generation (2023)","DOI":"10.1109\/CVPR52733.2024.00745"},{"key":"2_CR16","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: Openclip (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"2_CR17","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics yolov8 (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Ju, X., Zeng, A., Zhao, C., Wang, J., Zhang, L., Xu, Q.: HumanSD: a native skeleton-guided diffusion model for human image generation (2023)","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"2_CR19","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis (2023). https:\/\/arxiv.org\/abs\/2303.05511"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Gligen: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"2_CR22","unstructured":"Lian, L., Li, B., Yala, A., Darrell, T.: LLM-grounded diffusion: enhancing prompt understanding of text-to-image diffusion models with large language models. arXiv preprint arXiv:2305.13655 (2023)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Lin, J., Zeng, A., Wang, H., Zhang, L., Li, Y.: One-stage 3D whole-body mesh recovery with component aware transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21159\u201321168 (2023)","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. arXiv preprint arXiv:2305.08891 (2023)","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"2_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"2_CR26","unstructured":"Liu, X., et al.: Hyperhuman: hyper-realistic human generation with latent structural diffusion. arXiv preprint arXiv:2310.08579 (2023)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 34(6), 248:1\u2013248:16 (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"2_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"2_CR29","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"2_CR30","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning (2018)"},{"key":"2_CR31","unstructured":"OpenAI: DALL-E 3: Image generation model (2023). https:\/\/openai.com\/dall-e-3"},{"key":"2_CR32","unstructured":"OpenAI: GPT-4: enhancements and capabilities (2023). https:\/\/openai.com\/blog\/gpt-4"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv preprint arXiv:2212.09748 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"2_CR35","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"2_CR36","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR37","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, vol. 1, no. 2, p. 3 (2022)"},{"key":"2_CR38","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Ren, Y., Li, G., Chen, Y., Li, T.H., Liu, S.: Pirenderer: controllable portrait image generation via semantic neural rendering (2021)","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"2_CR42","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"2_CR43","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25278\u201325294 (2022)"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Shi, Z., Zhou, X., Qiu, X., Zhu, X.: Improving image captioning with better use of captions. arXiv preprint arXiv:2006.11807 (2020)","DOI":"10.18653\/v1\/2020.acl-main.664"},{"key":"2_CR45","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2022)"},{"key":"2_CR46","unstructured":"Team, G.: Gemini: a family of highly capable multimodal models (2023)"},{"key":"2_CR47","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: Boxdiff: text-to-image synthesis with training-free box-constrained diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7452\u20137461 (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"2_CR49","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789, vol. 2, no. 3, p. 5 (2022)"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, J.Y., Pepose, S., Joo, H., Ramanan, D., Malik, J., Kanazawa, A.: Perceiving 3D human-object spatial arrangements from a single image in the wild. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58610-2_3"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2_CR52","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73220-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:02:38Z","timestamp":1730577758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73220-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031732195","9783031732201"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73220-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}