{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:47Z","timestamp":1777889207296,"version":"3.51.4"},"reference-count":91,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202014,62332002,62425101"],"award-info":[{"award-number":["62202014,62332002,62425101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01303","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14039-14050","source":"Crossref","is-referenced-by-count":0,"title":["DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses"],"prefix":"10.1109","author":[{"given":"Yatian","family":"Pang","sequence":"first","affiliation":[{"name":"PKU Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"PKU Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Bin","sequence":"additional","affiliation":[{"name":"PKU Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhe","family":"Zheng","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francis E. H.","family":"Tay","sequence":"additional","affiliation":[{"name":"NUS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ser-Nam","family":"Lim","sequence":"additional","affiliation":[{"name":"UCF"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harry","family":"Yang","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Yuan","sequence":"additional","affiliation":[{"name":"PKU Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618153"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01764"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00097"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref9","article-title":"Magicdance: Realistic human dance video generation with motions & facial expressions transfer","author":"Chang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref13","article-title":"Vivid: Video virtual try-on using diffusion models","author":"Fang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Dreamoving: A human dance video generation framework based on diffusion models","author":"Feng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref16","article-title":"Affective faces for goal-driven dyadic communication","author":"Geng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref20","article-title":"Animatediff: Animate your personalized textto-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Id-animator: Zero-shot identity-preserving human video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_8"},{"key":"ref23","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref26","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref28","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00668"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"ref32","article-title":"Mobile portrait: Real-time one-shot neural head avatars on mobile devices","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_19"},{"key":"ref37","article-title":"Hyperhuman: Hyper-realistic human generation with latent structural diffusion","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00951"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref41","article-title":"Mimo: Controllable character video synthesis with spatial decomposed modeling","author":"Men","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref43","volume-title":"sd-webui-3d-open-pose-editor","year":"2024"},{"key":"ref44","article-title":"Envision3d: One image to 3d with anchor views interpolation","author":"Pang","year":"2024"},{"key":"ref45","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018224"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3687980"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00706"},{"key":"ref54","article-title":"Instadrag: Lightning fast and accurate drag based image editing emerging from videos","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref56","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref57","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref58","article-title":"Denoising diffusion implicit models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Song","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref60","article-title":"Motionfollower: Editing video motion via lightweight score-guided diffusion","author":"Tu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91578-9_8"},{"key":"ref63","article-title":"Vividpose: Advancing stable video diffusion for realistic human image animation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","first-page":"arXiv\u20132307","article-title":"Disco: Disentangled control for referring human dance generation in real world","author":"Wang","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4592-3"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32877"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02231-3"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref70","article-title":"Humanvid: Demystifying training data for camera-controllable human image animation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680836"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref76","article-title":"Follow-your-pose v2: Multiple-condition guided character image animation for stable pose control","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref79","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"Ip adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"Animatezero: Video diffusion models are zero-shot image animators","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00690"},{"key":"ref83","article-title":"Magictime: Time-lapse video generation models as metamorphic simulators","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref85","article-title":"Idol: Unified dual modal latent diffusion for human-centric joint video-depth generation","author":"Zhai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","first-page":"1","article-title":"Show-1: Marrying pixel and latent diffusion models for text-to-video generation","author":"Zhang","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref89","article-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref90","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref91","article-title":"Champ: Controllable and consistent human image animation with 3d parametric guidance","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445258.pdf?arnumber=11445258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:56Z","timestamp":1777612076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01303","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}