{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:25:53Z","timestamp":1780395953063,"version":"3.54.1"},"reference-count":38,"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\/iccv51701.2025.00780","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8330-8339","source":"Crossref","is-referenced-by-count":1,"title":["NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors"],"prefix":"10.1109","author":[{"given":"Yanrui","family":"Bin","sequence":"first","affiliation":[{"name":"Spatial Intelligence Group The Hong Kong Polytechnic University,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Hu","sequence":"additional","affiliation":[{"name":"ARC Lab Tencent PCG,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinya","family":"Chen","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[{"name":"Spatial Intelligence Group The Hong Kong Polytechnic University,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01289"},{"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":"10.1007\/978-3-642-33783-3_44"},{"key":"ref7","article-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation","author":"Caelles","year":"2019","journal-title":"arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref9","article-title":"Objaverse-xl: A universe of $10 ~\\mathrm{m}+3 ~\\mathrm{d}$ objects","author":"Deitke","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_16"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2013.421"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_44"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref15","article-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073232"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01839"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_25"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01645"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"ref24","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00083"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356528"},{"key":"ref27","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref32","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"In International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref33","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00077"},{"key":"ref36","article-title":"What matters when repurposing diffusion models for general dense perception tasks?","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3687971"},{"key":"ref38","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","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\/11445200.pdf?arnumber=11445200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:10:10Z","timestamp":1777612210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00780","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}