{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:57Z","timestamp":1777865457296,"version":"3.51.4"},"reference-count":70,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00699","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7451-7461","source":"Crossref","is-referenced-by-count":0,"title":["GeoMan: Temporally Consistent Human Geometry Estimation Using Image-to-Video Diffusion"],"prefix":"10.1109","author":[{"given":"Gwanghyun","family":"Kim","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueting","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koki","family":"Nagano","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianye","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Kautz","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Se Young","family":"Chun","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umar","family":"Iqbal","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref3","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Farooq Bhat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311"},{"key":"ref5","author":"Bochkovskii","year":"2024","journal-title":"Depth pro: Sharp monocular metric depth in less than a second. arXiv:2410"},{"key":"ref6","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref9","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","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\/ICCV.2019.00716"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01237"},{"key":"ref17","article-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022","journal-title":"arXiv preprint arXiv:2211.13221"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","author":"Ho","year":"2022","journal-title":"Video diffusion models. arXiv:2204"},{"key":"ref21","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2023","journal-title":"arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592415"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3231558"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref30","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref32","article-title":"CtrlAdapter: An efficient and versatile framework for adapting diverse controls to any diffusion model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392377"},{"key":"ref35","article-title":"Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars","author":"Martinez","year":"2024","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref38","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2023"},{"key":"ref39","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3019967"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref43","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"ref46","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"ICLR","author":"Salimans","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01622"},{"key":"ref48","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein","year":"2015"},{"key":"ref49","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00059"},{"key":"ref51","article-title":"MagicVideo-V2: Multistage high-aesthetic video generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume-title":"NeurIPS","author":"Wang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547978"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_27"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"ref57","article-title":"Depth any video with scalable synthetic data","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"ref63","article-title":"PaMIR: Parametric model-conditioned implicit representation for image-based human reconstruction","volume-title":"TPAMI","author":"Zheng","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref66","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","volume-title":"ICLR","author":"Zhang","year":"2025"},{"key":"ref67","volume-title":"I2VGen-XL: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459871"},{"key":"ref69","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00948","article-title":"SIFU: Sideview conditioned implicit function for real-world usable clothed human reconstruction","volume-title":"CVPR","author":"Zhang","year":"2024"},{"key":"ref70","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","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\/11443528.pdf?arnumber=11443528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:36:09Z","timestamp":1777530969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00699","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}