{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:03:55Z","timestamp":1783530235091,"version":"3.55.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019014","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["CJGJZD20220517142402006"],"award-info":[{"award-number":["CJGJZD20220517142402006"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019014","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["JCYJ20220818101014030"],"award-info":[{"award-number":["JCYJ20220818101014030"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Fund of Tsinghua University\u2014Tencent Joint Laboratory for Internet Innovation Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tcsvt.2025.3559931","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T14:06:38Z","timestamp":1744380398000},"page":"9865-9877","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Text-Guided 3D-Aware Generation With Score Distillation on 3D Distribution"],"prefix":"10.1109","volume":"35","author":[{"given":"Yiji","family":"Cheng","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5146-7685","authenticated-orcid":false,"given":"Fei","family":"Yin","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoke","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xintong","family":"Yu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shikun","family":"Feng","sequence":"additional","affiliation":[{"name":"Baidu Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6427-1024","authenticated-orcid":false,"given":"Yujiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-4549","authenticated-orcid":false,"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. ICML","author":"Reed"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref5","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref6","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref7","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. ICML","author":"Nichol"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref9","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NeurIPS","author":"Saharia"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref13","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref14","article-title":"ERNIE-ViLG: Unified generative pre-training for bidirectional vision-language generation","author":"Zhang","year":"2021","journal-title":"arXiv:2112.15283"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3351601"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591566"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00439"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01612"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref27","first-page":"11970","article-title":"Debiasing scores and prompts of 2D diffusion for view-consistent text-to-3D generation","volume-title":"Proc. NeurIPS","author":"Hong"},{"key":"ref28","article-title":"Re-imagine the negative prompt algorithm: Transform 2D diffusion into 3D, alleviate Janus problem and beyond","author":"Armandpour","year":"2023","journal-title":"arXiv:2304.04968"},{"key":"ref29","first-page":"8406","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref32","first-page":"1","article-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref33","article-title":"GaussianCube: A structured and explicit radiance representation for 3D generative modeling","author":"Zhang","year":"2024","journal-title":"arXiv:2403.19655"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285479"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285153"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237815"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_27"},{"key":"ref38","first-page":"1","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. ICLR","author":"Poole"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00537"},{"key":"ref40","first-page":"1","article-title":"MVDream: Multi-view diffusion for 3D generation","volume-title":"Proc. ICLR","author":"Shi"},{"key":"ref41","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv:2212.08751"},{"key":"ref42","article-title":"Shap-E: Generating conditional 3D implicit functions","author":"Jun","year":"2023","journal-title":"arXiv:2305.02463"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01766"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01973"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409184"},{"key":"ref47","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. ICML","author":"Ramesh"},{"key":"ref48","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref49","first-page":"1","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. ICLR","author":"Guo"},{"key":"ref50","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref52","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref53","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024","journal-title":"arXiv:2405.09818"},{"key":"ref54","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv:2409.18869"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00097"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3592094"},{"key":"ref57","first-page":"4566","article-title":"DreamWaltz: Make a scene with complex 3D animatable avatars","volume-title":"Proc. NeurIPS","author":"Huang"},{"key":"ref58","first-page":"4915","article-title":"HeadSculpt: Crafting 3D head avatars with text","volume-title":"Proc. NeurIPS","author":"Han"},{"key":"ref59","first-page":"10516","article-title":"DreamHuman: Animatable 3D avatars from text","volume-title":"Proc. NeurIPS","author":"Kolotouros"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref61","first-page":"1","article-title":"DreamGaussian: Generative Gaussian splatting for efficient 3D content creation","volume-title":"Proc. ICLR","author":"Tang"},{"key":"ref62","first-page":"1","article-title":"Instant3D: Fast text-to-3D with sparse-view generation and large reconstruction model","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref63","first-page":"20154","article-title":"GRAF: Generative radiance fields for 3D-aware image synthesis","volume-title":"Proc. NeurIPS","author":"Schwarz"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref67","first-page":"31841","article-title":"GET3D: A generative model of high quality 3D textured shapes learned from images","volume-title":"Proc. NeurIPS","author":"Gao"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00041"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407135"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01759"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"ref72","first-page":"8882","article-title":"ShapeCrafter: A recursive text-conditioned 3D shape generation model","volume-title":"Proc. NeurIPS","author":"Fu"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248143"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref76","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref79","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","author":"Alayrac"},{"key":"ref80","first-page":"1","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. ICLR","author":"Karras"},{"key":"ref81","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref83","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NeurIPS","author":"Heusel"},{"key":"ref84","first-page":"1","article-title":"Benchmark for compositional text-to-image synthesis","volume-title":"Proc. NeurIPS","author":"Park"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9666791"},{"key":"ref90","first-page":"30105","article-title":"StyleGAN-T: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proc. ICML","author":"Sauer"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01314"},{"key":"ref92","first-page":"1","article-title":"3D generation on ImageNet","volume-title":"Proc. ICLR","author":"Skorokhodov"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11192799\/10963753.pdf?arnumber=10963753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:40:08Z","timestamp":1759772408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10963753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":92,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3559931","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}