{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:07:16Z","timestamp":1784268436214,"version":"3.55.0"},"reference-count":115,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB36066"],"award-info":[{"award-number":["2022YFB36066"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01318","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14205-14217","source":"Crossref","is-referenced-by-count":1,"title":["GUAVA: Generalizable Upper Body 3D Gaussian Avatar"],"prefix":"10.1109","author":[{"given":"Dongbin","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfei","family":"Liu","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijian","family":"Lin","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Zhu","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghan","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00444"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01972"},{"key":"ref3","article-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024","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 preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref7","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","author":"Chang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","author":"Chen","year":"2023","journal-title":"Videocrafter1: Open diffusion models for high-quality video generation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00698"},{"key":"ref10","author":"Chen","year":"2024","journal-title":"Generalizable human gaussians from single-view image"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01989"},{"key":"ref12","article-title":"Adversariallyguided portrait matting","author":"Chicherin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1838"},{"key":"ref15","article-title":"Gpavatar: Generalizable and precise head avatar from image (s)","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1134-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00680"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_19"},{"key":"ref21","article-title":"Soft-gated warping-gan for pose-guided person image synthesis","volume-title":"Advances in neural information processing systems","volume":"31","author":"Dong","year":"2018"},{"key":"ref22","first-page":"2127","article-title":"Hamba: Single-view 3d hand reconstruction with graph-guided biscanning mamba","volume":"37","author":"Dong","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref31","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref33","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"arXiv preprint","author":"Hu","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01930"},{"key":"ref36","article-title":"Eva-gaussian: 3d gaussian-based real-time human novel view synthesis under diverse camera settings","volume-title":"arXiv preprint","author":"Hu","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00824"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01238"},{"key":"ref43","first-page":"21696","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_25"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555376"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1099"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680674"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00169"},{"key":"ref55","article-title":"Teaser: Token enhanced spatial modeling for expressions reconstruction","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref57","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00257"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_2"},{"key":"ref62","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2367"},{"key":"ref64","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"ref71","article-title":"Geometry-contrastive gan for facial expression transfer","author":"Qiao","year":"2018","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28256"},{"key":"ref74","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00241"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00021"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4444"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00359"},{"key":"ref83","article-title":"First order motion model for image animation","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Siarohin"},{"key":"ref84","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref85","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref86","article-title":"Scorebased generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3201904"},{"key":"ref88","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref89","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_1"},{"key":"ref91","article-title":"Disco: Disentangled control for realistic human dance generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00991"},{"key":"ref93","article-title":"Magicvideo-v2: Multistage high-aesthetic video generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011290"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00177"},{"key":"ref98","article-title":"One shot, one talk: Whole-body talking avatar from a single image","author":"Xiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00189"},{"key":"ref100","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00091"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_20"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02448"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00829"},{"key":"ref110","article-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3626316"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01861"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3562651"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"}],"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\/11444024.pdf?arnumber=11444024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:22Z","timestamp":1777530082000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444024\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":115,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01318","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}