{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T01:26:06Z","timestamp":1773883566817,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["2024YFB4708900"],"award-info":[{"award-number":["2024YFB4708900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62403401"],"award-info":[{"award-number":["62403401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225309"],"award-info":[{"award-number":["62225309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"in part by Guangdong Basic and Applied Basic Research Foundation","award":["2024A1515011992"],"award-info":[{"award-number":["2024A1515011992"]}]},{"name":"in part by Guangdong Basic and Applied Basic Research Foundation","award":["2026A1515012323"],"award-info":[{"award-number":["2026A1515012323"]}]},{"name":"in part by Guangdong Provincial Project","award":["2024QN11X127"],"award-info":[{"award-number":["2024QN11X127"]}]},{"DOI":"10.13039\/501100018526","name":"AI Research and Learning Base of Urban Culture","doi-asserted-by":"publisher","award":["2023WZJD008"],"award-info":[{"award-number":["2023WZJD008"]}],"id":[{"id":"10.13039\/501100018526","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3671692","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:40:22Z","timestamp":1773348022000},"page":"2570-2583","source":"Crossref","is-referenced-by-count":0,"title":["SCSV: Spatial-Temporal Consistent Dynamic 3D Scene Generation From Sparse Views"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5563-8557","authenticated-orcid":false,"given":"Junfeng","family":"Li","sequence":"first","affiliation":[{"name":"Thrust of Robotics and Autonomous Systems and the Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9233-4238","authenticated-orcid":false,"given":"Junjie","family":"He","sequence":"additional","affiliation":[{"name":"Thrust of Robotics and Autonomous Systems and the Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Thrust of Robotics and Autonomous Systems and the Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2418-7610","authenticated-orcid":false,"given":"Tianyu","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6077-4951","authenticated-orcid":false,"given":"Shunbo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9405-8232","authenticated-orcid":false,"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Thrust of Robotics and Autonomous Systems and the Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9959-1634","authenticated-orcid":false,"given":"Hesheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1576-9408","authenticated-orcid":false,"given":"Haoang","family":"Li","sequence":"additional","affiliation":[{"name":"Thrust of Robotics and Autonomous Systems and the Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3400149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3573524"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0674"},{"key":"ref6","first-page":"1","article-title":"SV4D: Dynamic 3D content generation with multi-frame and multi-view consistency","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref7","first-page":"1","article-title":"GenXD: Generating any 3D and 4D scenes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"ref9","first-page":"13695","article-title":"DimensionX: Create any 3D and 4D scenes from a single image with decoupled video diffusion","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sun"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1810"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01651"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"ref13","first-page":"1","article-title":"VD3D: Taming large video diffusion transformers for 3D camera control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bahmani"},{"key":"ref14","article-title":"Novel view extrapolation with video diffusion priors","author":"Liu","year":"2024","journal-title":"arXiv:2411.14208"},{"key":"ref15","first-page":"1","article-title":"NVS-solver: Video diffusion model as zero-shot novel view synthesizer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"You"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967590"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01345"},{"key":"ref20","first-page":"1","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Poole"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3539935"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref25","first-page":"1","article-title":"DreamGaussian: Generative Gaussian splatting for efficient 3D content creation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3574929"},{"key":"ref29","first-page":"1","article-title":"Flex3D: Feed-forward 3D generation with flexible reconstruction model and input view curation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref30","first-page":"1","article-title":"LRM: Large reconstruction model for single image to 3D","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref31","article-title":"LucidDreamer: Domain-free generation of 3D Gaussian splatting scenes","author":"Chung","year":"2023","journal-title":"arXiv:2311.13384"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"ref34","article-title":"ViewCrafter: Taming video diffusion models for high-fidelity novel view synthesis","author":"Yu","year":"2024","journal-title":"arXiv:2409.02048"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref36","first-page":"1","article-title":"EG4D: Explicit generation of 4D object without score distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sun"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref38","article-title":"Efficient4D: Fast dynamic 3D object generation from a single-view video","author":"Pan","year":"2024","journal-title":"arXiv:2401.08742"},{"key":"ref39","first-page":"1","article-title":"Diffusion2: Dynamic 3D content generation via score composition of video and multi-view diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1987"},{"key":"ref42","article-title":"SV4D 2.0: Enhancing spatio-temporal consistency in multi-view video diffusion for high-quality 4D generation","author":"Yao","year":"2025","journal-title":"arXiv:2503.16396"},{"key":"ref43","article-title":"Human-VDM: Learning single-image 3D human Gaussian splatting from video diffusion models","author":"Liu","year":"2024","journal-title":"arXiv:2409.02851"},{"key":"ref44","article-title":"PSHuman: Photorealistic single-image 3D human reconstruction using cross-scale multiview diffusion and explicit remeshing","author":"Li","year":"2024","journal-title":"arXiv:2409.10141"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref46","first-page":"14184","article-title":"LHM: Large animatable human reconstruction model for single image to 3D in seconds","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Qiu"},{"issue":"2","key":"ref47","first-page":"3","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","volume":"1","author":"Hu"},{"key":"ref48","article-title":"4Real-video-v2: Fused view-time attention and feedforward reconstruction for 4D scene generation","author":"Wang","year":"2025","journal-title":"arXiv:2506.18839"},{"key":"ref49","article-title":"MoVieS: Motion-aware 4D dynamic view synthesis in one second","author":"Lin","year":"2025","journal-title":"arXiv:2507.10065"},{"key":"ref50","article-title":"4DGT: Learning a 4D Gaussian transformer using real-world monocular videos","author":"Xu","year":"2025","journal-title":"arXiv:2506.08015"},{"key":"ref51","first-page":"1","article-title":"Reconstruct, inpaint, test-time finetune: Dynamic novel-view synthesis from monocular videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref52","first-page":"25571","article-title":"Free4D: Tuning-free 4D scene generation with spatial\u2013temporal consistency","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Liu"},{"key":"ref53","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref54","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv:2503.20314"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01246"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02125"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref58","first-page":"1","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ravi"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_12"},{"key":"ref60","first-page":"1","article-title":"Human motion diffusion model","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tevet"},{"key":"ref61","article-title":"VACE: All-in-one video creation and editing","author":"Jiang","year":"2025","journal-title":"arXiv:2503.07598"},{"key":"ref62","first-page":"1","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bochkovskiy"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"issue":"34","key":"ref64","first-page":"1","article-title":"gsplat: An open-source library for Gaussian splatting","volume":"26","author":"Ye","year":"2025","journal-title":"J. Mach. Learn. Res."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11433509.pdf?arnumber=11433509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:41:42Z","timestamp":1773862902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3671692","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}