{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:16:47Z","timestamp":1778080607578,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6250070674"],"award-info":[{"award-number":["6250070674"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Leading Innovative and Entrepreneur Team Introduction Program","award":["2024R01007"],"award-info":[{"award-number":["2024R01007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/jstsp.2026.3662496","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:36Z","timestamp":1770671136000},"page":"192-201","source":"Crossref","is-referenced-by-count":2,"title":["StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6344-2824","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"first","affiliation":[{"name":"Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7945-6028","authenticated-orcid":false,"given":"Yiwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6885-7595","authenticated-orcid":false,"given":"Yijun","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0088-4398","authenticated-orcid":false,"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5886-0906","authenticated-orcid":false,"given":"Zhenglin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6067-1334","authenticated-orcid":false,"given":"Wenjia","family":"Jiang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0314-2422","authenticated-orcid":false,"given":"Zhibin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5277-8709","authenticated-orcid":false,"given":"Bin","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5570-2710","authenticated-orcid":false,"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-7458","authenticated-orcid":false,"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2542-9204","authenticated-orcid":false,"given":"Chenxi","family":"Song","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref6","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref9","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref11","first-page":"82","article-title":"Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2016"},{"key":"ref12","first-page":"31841","article-title":"GET3D: A generative model of high quality 3D textured shapes learned from images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref15","first-page":"10021","article-title":"LION: Latent point diffusion models for 3D shape generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Vahdat","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356571"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201401"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00366"},{"key":"ref19","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"ref21","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref28","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3124981"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref34","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref41","first-page":"8406","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01255"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00307"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322984"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00442"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00537"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"ref52","first-page":"1","article-title":"StyleNeRF: A style-based 3D aware generator for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref55","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref57","first-page":"1","article-title":"DreamGaussian: Generative gaussian splatting for efficient 3D content creation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Tang","year":"2023"},{"key":"ref58","article-title":"TripoSR: Fast 3D object reconstruction from a single image","author":"Tochilkin","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11458039\/11382190.pdf?arnumber=11382190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:52:49Z","timestamp":1774986769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11382190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":60,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2026.3662496","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}