{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:55:00Z","timestamp":1788969300727,"version":"build-2803163510"},"reference-count":120,"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\/iccv51701.2025.01266","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13639-13650","source":"Crossref","is-referenced-by-count":5,"title":["TACO: Taming Diffusion for In-the-Wild Video Amodal Completion"],"prefix":"10.1109","author":[{"given":"Ruijie","family":"Lu","sequence":"first","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Ni","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diwen","family":"Wan","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"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","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref8","article-title":"Learnable gated temporal shift module for deep video inpainting","author":"Chang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02131"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561754"},{"key":"ref12","volume-title":"Blender - a 3D modelling and rendering package","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00773"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00146"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_42"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref26","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Guo","year":"2024"},{"key":"ref27","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref28","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3064065"},{"key":"ref30","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Tracking any object amodally","author":"Hsieh","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00322"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_3"},{"key":"ref35","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02288"},{"key":"ref37","article-title":"Leo-vl: Towards 3d visionlanguage generalists via data scaling with efficient representation","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.23"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00401"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01420"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"ref45","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.4324\/9781315009292"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_42"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_42"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801835"},{"key":"ref52","article-title":"Puppet-master: Scaling interactive video generation as a motion prior for part-level dynamics","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref54","article-title":"Dreamitate: Real-world visuomotor policy learning via video generation","volume-title":"Conference on Robot Learning (CoRL)","author":"Liang","year":"2024"},{"key":"ref55","article-title":"Variational amodal object completion","author":"Ling","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_15"},{"key":"ref60","article-title":"Building interactable replicas of complex articulated objects via gaussian splatting","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu","year":"2025"},{"key":"ref61","article-title":"Objectcentric learning with slot attention","author":"Locatello","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02493"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00695"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0810"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00565"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00377"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00313"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01977-6"},{"key":"ref71","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref72","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Ramesh","year":"2021"},{"key":"ref73","article-title":"Sam 2: Segment anything in images and videos","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ravi","year":"2025"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00914"},{"key":"ref75","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02127"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00627"},{"key":"ref80","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Song","year":"2020"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01626"},{"key":"ref83","article-title":"Intex: Interactive text-to-texture synthesis via unified depth-aware inpainting","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01326"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1037\/a0029333"},{"key":"ref90","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Rich Walke","year":"2023"},{"key":"ref91","article-title":"Superpoint gaussian splatting for real-time high-fidelity dynamic scene reconstruction","author":"Wan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_27"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref95","first-page":"161","article-title":"Experimentelle studien uber das sehen von bewegung","volume":"61","author":"Wertheimer","year":"1912","journal-title":"Zeitschrift fur psychologie"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1515\/gth-2017-0007"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01188"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref100","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00869"},{"key":"ref103","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref106","article-title":"Cogvideox: Text-tovideo diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref107","article-title":"Self-supervised amodal video object segmentation","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref112","article-title":"Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02645"},{"key":"ref115","volume-title":"Self-supervised scene deocclusion. In Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhan","year":"2020"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00684"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.320"},{"key":"ref119","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Conference on Robot Learning","author":"Zhu","year":"2023"},{"key":"ref120","article-title":"Videomv: Consistent multi-view generation based on large video generative model","author":"Zuo","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\/11444423.pdf?arnumber=11444423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:07Z","timestamp":1777611967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":120,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01266","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}