{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:37:16Z","timestamp":1778081836290,"version":"3.51.4"},"reference-count":113,"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\/iccv51701.2025.01265","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13625-13637","source":"Crossref","is-referenced-by-count":1,"title":["T2Bs: Text-to-Character Blendshapes via Video Generation"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Luo","sequence":"first","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Vasilkovsky","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladislav","family":"Shakhrai","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Liu","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiye","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Tulyakov","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Wonka","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Ying","family":"Lee","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Davis","sequence":"additional","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref3","author":"Bahmani","year":"2024","journal-title":"Vd3d: Taming large video diffusion transformers for 3d camera control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18034\/ajase.v8i1.9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.249"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00229"},{"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\/ICCV51070.2023.02033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3395208"},{"issue":"8","key":"ref15","first-page":"242","article-title":"The proposed uscf rating system, its development, theory, and applications","volume":"22","author":"Elo","year":"1967","journal-title":"Chess life"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2403"},{"key":"ref17","author":"Guo","year":"2024","journal-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control"},{"key":"ref18","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0218"},{"key":"ref20","author":"He","year":"2024","journal-title":"Cameractrl: Enabling camera control for text-to-video generation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref22","author":"Ho","year":"2020","journal-title":"Denoising diffusion probabilistic models"},{"key":"ref23","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref24","author":"Hong","year":"2024","journal-title":"Lrm: Large reconstruction model for single image to 3d"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555394"},{"key":"ref26","article-title":"A 3D Face Model for Pose and Illumination Invariant Face Recognition","volume-title":"Genova, Italy","year":"2009"},{"key":"ref27","author":"Jiang","year":"2023","journal-title":"Consistent4d: Consistent 360deg dynamic object generation from monocular video"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1185657.1185857"},{"key":"ref29","author":"Jun","year":"2023","journal-title":"Shap-e: Generating conditional 3d implicit functions"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00578"},{"key":"ref32","author":"Li","year":"2024","journal-title":"Vivid-zoo: Multi-view video generation with diffusion model"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778769"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462019"},{"key":"ref35","author":"Li","year":"2023","journal-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref37","article-title":"Dreammesh4d: Video-to-4d generation with sparse-controlled gaussianmesh hybrid representation","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00623"},{"key":"ref39","article-title":"Magic3d: Highresolution text-to-3d content creation","author":"Lin","year":"2023","journal-title":"In CVPR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01309"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2359"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01968"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref46","author":"Liu","year":"2023","journal-title":"Meshdiffusion: Score-based generative 3d mesh modeling"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01841"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00085"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00965"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3618368"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref56","author":"Nichol","year":"2022","journal-title":"Point-e: A system for generating 3d point clouds from complex prompts"},{"key":"ref57","article-title":"Video generation models as world simulators","year":"2024","journal-title":"OpenAI"},{"key":"ref58","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"In ICLR"},{"key":"ref59","article-title":"Magic 123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors","author":"Qian","year":"2024","journal-title":"ICLR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"ref61","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref62","author":"Ren","year":"2023","journal-title":"Dreamgaussian4d: Generative 4d gaussian splatting"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1810"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref65","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555402"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"ref68","author":"Shen","year":"2021","journal-title":"Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3592430"},{"key":"ref70","author":"Shi","year":"2023","journal-title":"Zero123++: a single image to consistent multiview diffusion base model"},{"key":"ref71","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2024","journal-title":"In ICLR"},{"key":"ref72","author":"Singer","year":"2023","journal-title":"Text-to-4d dynamic scene generation"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref74","author":"Tang","year":"2024","journal-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00501"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00154"},{"key":"ref77","author":"Unterthiner","year":"2018","journal-title":"Fvd: A new metric for video generation"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01651"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00025"},{"key":"ref82","author":"Wang","year":"2023","journal-title":"Gaussianhead: Impressive head avatars with learnable gaussian diffusion"},{"key":"ref83","author":"Wang","year":"2024","journal-title":"Shape of motion: 4d reconstruction from a single video"},{"key":"ref84","author":"Wang","year":"2022","journal-title":"Rodin: A generative model for sculpting 3d digital avatars using diffusion"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4173"},{"key":"ref86","article-title":"Prolificdreamer: Highfidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref88","author":"Watson","year":"2024","journal-title":"Controlling space and time with diffusion models"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02427"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_21"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00177"},{"key":"ref94","author":"Xiang","year":"2024","journal-title":"Structured 3d latents for scalable and versatile 3d generation"},{"key":"ref95","author":"Xie","year":"2024","journal-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency"},{"key":"ref96","author":"Xu","year":"2024","journal-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models"},{"key":"ref97","author":"Xu","year":"2024","journal-title":"Grm: Large gaussian reconstruction model for efficient 3d reconstruction and generation"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01572"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00288"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref101","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-tovideo diffusion models with an expert transformer"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref103","author":"Yin","year":"2023","journal-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency"},{"key":"ref104","article-title":"4real: Towards photorealistic 4d scene generation via video diffusion models","author":"Yu","year":"2024","journal-title":"In NeurIPS"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00091"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_27"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0488"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref109","author":"Zhao","year":"2023","journal-title":"Animate124: Animating one image to 4d dynamic scene"},{"key":"ref110","author":"Zhao","year":"2023","journal-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_9"},{"key":"ref112","article-title":"Hifa: High-fidelity text-to3d with advanced diffusion guidance","author":"Zhu","year":"2023","journal-title":"ICLR"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00983"}],"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\/11444023.pdf?arnumber=11444023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:54Z","timestamp":1777613334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":113,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01265","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}