{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:25:16Z","timestamp":1780392316549,"version":"3.54.1"},"reference-count":94,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306295,62225207,62436008"],"award-info":[{"award-number":["62306295,62225207,62436008"]}],"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\/iccv51701.2025.00487","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5122-5133","source":"Crossref","is-referenced-by-count":6,"title":["SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Yang","sequence":"first","affiliation":[{"name":"USTC,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixing","family":"Lu","sequence":"additional","affiliation":[{"name":"CMU,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingyu","family":"Wu","sequence":"additional","affiliation":[{"name":"USTC,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhai","sequence":"additional","affiliation":[{"name":"USTC,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Yi","sequence":"additional","affiliation":[{"name":"SJTU,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[{"name":"USTC,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"SJTU,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"USTC,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junting","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"ref3","article-title":"Generalizable human gaussians from single-view image","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Dancetogether! identity-preserving multi-person interactive video generation","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01829"},{"issue":"70","key":"ref7","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0992"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02097"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_2"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446237"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01237"},{"key":"ref17","article-title":"Sampling 3d gaussian scenes in seconds with latent diffusion models","author":"Henderson","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00858"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00824"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3592415"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref27","article-title":"Dreamhuman: Animatable 3d avatars from text","author":"Kolotouros","year":"2023"},{"key":"ref28","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref29","first-page":"24741","article-title":"Neural human performer: Learning generalizable radiance fields for human performance rendering","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Kwon","year":"2021"},{"key":"ref30","article-title":"Neural image-based avatars: Generalizable radiance fields for human avatar modeling","author":"Kwon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1783"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_26"},{"key":"ref33","volume-title":"Flux","year":"2024"},{"key":"ref34","article-title":"Gaussiananything: Interactive point cloud latent diffusion for 3d generation","volume-title":"ICLR","author":"Lan","year":"2025"},{"key":"ref35","article-title":"Dispose: Disentangling pose guidance for controllable human image animation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Pshuman: Photorealistic single-view human reconstruction using cross-scale diffusion","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01656"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"ref39","article-title":"Diffsplat: Repurposing image diffusion models for scalable gaussian splat generation","author":"Lin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Playground v3: Improving text-to-image alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00635"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01197"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01973"},{"key":"ref46","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3658217"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"ref52","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Variational autoencoder for deep learning of images, labels and captions","volume-title":"Advances in neural information processing systems","volume":"29","author":"Pu","year":"2016"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51701.2025.01316","article-title":"Lhm: Large animatable human reconstruction model for single image to 3d in one second","author":"Qiu","year":"2025"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"ref58","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint"},{"key":"ref59","first-page":"19313","article-title":"Light field networks: Neural scene representations with single-evaluation rendering","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Sitzmann","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01972"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref63","article-title":"Intex: Interactive text-to-texture synthesis via unified depth-aware inpainting","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00597"},{"key":"ref65","volume-title":"Mochi 1","year":"2024"},{"key":"ref66","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation","year":"2025"},{"key":"ref68","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"crossref","DOI":"10.1109\/TVCG.2025.3618268","article-title":"Wonderhuman: Hallucinating unseen parts in dynamic 3d human reconstruction","author":"Wang","year":"2025"},{"key":"ref70","article-title":"Template-free single-view 3d human digitalization with diffusion-guided lrm","author":"Weng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02000"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00940"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01872"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"ref76","article-title":"Atlas gaussians diffusion for 3d generation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01541"},{"key":"ref78","article-title":"Egochoir: Capturing 3d human-object interaction regions from egocentric views","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00956"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00306"},{"key":"ref83","article-title":"The dawn of video generation: Preliminary explorations with sora-like models","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","article-title":"Root mean square layer normalization","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Zhang","year":"2019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref87","article-title":"e3gen: Efficient, expressive and editable avatars generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0343"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00948"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00759"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01861"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00783"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050505"},{"key":"ref94","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\/11445935.pdf?arnumber=11445935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:39:51Z","timestamp":1777531191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00487","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}