{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:39Z","timestamp":1777865319398,"version":"3.51.4"},"reference-count":98,"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":["2022YFF0902401"],"award-info":[{"award-number":["2022YFF0902401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025108"],"award-info":[{"award-number":["62025108"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00995","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10686-10697","source":"Crossref","is-referenced-by-count":0,"title":["Tera: Rethinking Text-Guided Realistic 3D Avatar Generation"],"prefix":"10.1109","author":[{"given":"Yanwen","family":"Wang","sequence":"first","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyu","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Cao","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinxin","family":"Zuo","sequence":"additional","affiliation":[{"name":"Concordia University,Montreal,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","first-page":"40","article-title":"Learning representations and generative models for 3d point clouds","volume-title":"International conference on machine learning","author":"Achlioptas"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2010.65"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00541"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6687(96)00017-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref8","author":"Bai","year":"2025","journal-title":"Qwen2. 5-vl technical report"},{"key":"ref9","author":"Balaji","year":"2022","journal-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref11","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00097"},{"key":"ref13","first-page":"16123","article-title":"Efficient geometry-aware 3d generative adversarial networks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Eric R"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref17","author":"Cheng","year":"2019","journal-title":"Meshgan: Non-linear 3d morphable models of faces"},{"key":"ref18","article-title":"Progressive3d: Progressively local editing for text-to-3d content creation with complex semantic prompts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Cheng"},{"key":"ref19","author":"Cheong","year":"2024","journal-title":"Boosting camera motion control for video diffusion transformers"},{"issue":"4","key":"ref20","first-page":"1","article-title":"The light stages and their applications to photoreal digital actors","volume":"2","author":"Debevec","year":"2012","journal-title":"SIGGRAPH Asia"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591552"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01331"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356571"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref26","author":"He","year":"2024","journal-title":"Cameractrl: Enabling camera control for text-to-video generation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_15"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref29","article-title":"Classifier-free diffusion guidance","author":"Ho","journal-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications"},{"key":"ref30","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","author":"Hong","year":"2022","journal-title":"Eva3d: Compositional 3d human generation from 2d image collections"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"ref33","author":"Hou","year":"2024","journal-title":"Training-free camera control for video generation"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_21"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0202"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00196"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687686"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0462"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_7"},{"key":"ref44","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00150"},{"key":"ref46","article-title":"Flow matching for generative modeling","volume-title":"11th International Conference on Learning Representations","author":"Lipman"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"ref48","author":"Liu","year":"2024","journal-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref51","author":"Ma","year":"2024","journal-title":"Latte: Latent diffusion transformer for video generation"},{"key":"ref52","first-page":"33826","article-title":"X-oscar: a progressive framework for highquality text-guided 3d animatable avatar generation","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Ma"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref57","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref59","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00396"},{"key":"ref66","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2024","journal-title":"ICLR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00256"},{"key":"ref68","author":"Tochilkin","year":"2024","journal-title":"Triposr: Fast 3d object reconstruction from a single image"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_22"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01612"},{"key":"ref74","article-title":"Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling","volume":"29","author":"Wu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3873"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"ref78","author":"Yang","year":"2024","journal-title":"Qwen2. 5 technical report"},{"key":"ref79","author":"Yi","year":"2023","journal-title":"Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00761"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"ref82","author":"Zeng","year":"2023","journal-title":"Avatarbooth: High-quality and customizable 3d human avatar generation"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00151"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28540"},{"key":"ref85","article-title":"Fate: Fullhead gaussian avatar with textural editing from monocular video","author":"Zhang","year":"2025","journal-title":"Fate: Fullhead gaussian avatar with textural editing from monocular video"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681409"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02013"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref91","author":"Zheng","year":"2024","journal-title":"Cami2v: Camera-controlled image-to-video diffusion model"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050505"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3102128"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00036"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_16"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.fmre.2025.12.031"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02450"}],"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\/11445957.pdf?arnumber=11445957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:01Z","timestamp":1777529761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00995","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}