{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:12:03Z","timestamp":1784268723494,"version":"3.55.0"},"reference-count":83,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01231","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13248-13258","source":"Crossref","is-referenced-by-count":6,"title":["SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation"],"prefix":"10.1109","author":[{"given":"Chun-Han","family":"Yao","sequence":"first","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Xie","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikram","family":"Voleti","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaizu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref2","article-title":"SynCamMaster: Synchronizing multi-camera video generation from diverse viewpoints","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Stable Video Diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","article-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation","author":"Caelles","year":"2019","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"CT4D: Consistent text-to-4D generation with animatable meshes","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"3D- Adapter: Geometry-consistent multi-view diffusion for high-quality 3D generation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref9","article-title":"Objaverse-xl: A universe of $10\\ \\mathrm{m}+3$ D objects","author":"Deitke","year":"2023","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref12","article-title":"GaussianFlow: Splatting gaussian dynamics for 4D content creation","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02431"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref15","article-title":"StableDreamer: Taming noisy score distillation sampling for text-to-3D","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref17","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv"},{"key":"ref18","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref19","article-title":"LRM: Large reconstruction model for single image to 3D","author":"Hong","year":"2024","journal-title":"ICLR"},{"key":"ref20","article-title":"LEAP: Liberate sparse-view 3D modeling from camera poses","author":"Jiang","year":"2024","journal-title":"ICLR"},{"key":"ref21","article-title":"Animate3D: Animating any 3D model with multi-view video diffusion","author":"Jiang","year":"2024","journal-title":"NeurIPS"},{"key":"ref22","article-title":"Consistent4D: Consistent 360\u00b0 dynamic object generation from monocular video","author":"Jiang","year":"2024","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02100"},{"key":"ref24","article-title":"Vivid-ZOO: Multi-view video generation with diffusion model","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Instant3D: Fast text-to-3D with sparse-view generation and large reconstruction model","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref26","article-title":"SweetDreamer: Aligning geometric priors in 2D diffusion for consistent text-to-3D","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref30","article-title":"One-2\u20133-45: Any single image to 3D mesh in 45 seconds without per-shape optimization","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref33","article-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2024","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref36","article-title":"Enhancing high-resolution 3D generation through pixel-wise gradient clipping","author":"Pan","year":"2024","journal-title":"ICLR"},{"key":"ref37","article-title":"Fast dynamic 3D object generation from a single-view video","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref39","author":"Pont-Tuset","year":"2017","journal-title":"The 2017 davis challenge on video object segmentation"},{"key":"ref40","article-title":"DreamFusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref42","article-title":"Bringing objects to life: 4D generation from 3D objects","author":"Rahamim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"DreamGaussian4D: Generative 4D gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"L4GM: Large 4D gaussian reconstruction model","author":"Ren","year":"2024","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"ref48","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"TOSS: High-quality text-guided novel view synthesis from a single image","author":"Shi","year":"2024","journal-title":"ICLR"},{"key":"ref50","article-title":"MVDream: Multi-view diffusion for 3D generation","author":"Shi","year":"2024","journal-title":"ICLR"},{"key":"ref51","article-title":"Make-A- Video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref52","article-title":"Text-to-4D dynamic scene generation","author":"Singer","year":"2023","journal-title":"ICML"},{"key":"ref53","article-title":"DreamCraft3D: Hierarchical 3D generation with bootstrapped diffusion prior","author":"Sun","year":"2024","journal-title":"ICLR"},{"key":"ref54","article-title":"EG4D: Explicit generation of 4D object without score distillation","author":"Sun","year":"2025","journal-title":"ICLR"},{"key":"ref55","article-title":"DimensionX: Create any 3D and 4D scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"DreamGaussian: Generative gaussian splatting for efficient 3D content creation","author":"Tang","year":"2024","journal-title":"ICLR"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32787"},{"key":"ref58","article-title":"TripoSR: Fast 3D object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"MCVD: Masked conditional video diffusion for prediction, generation, and interpolation","author":"Voleti","year":"2022","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01651"},{"key":"ref63","article-title":"ImageDream: Image-prompt multi-view diffusion for 3D generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"PF-LRM: Pose-free large reconstruction model for joint pose and shape prediction","author":"Wang","year":"2024","journal-title":"ICLR"},{"key":"ref65","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref66","article-title":"MeshLRM: Large reconstruction model for highquality mesh","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Consistent123: Improve consistency for one image to 3D object synthesis","author":"Weng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02427"},{"key":"ref69","article-title":"SV4D: Dynamic 3D content generation with multi-frame and multi-view consistency","author":"Xie","year":"2025","journal-title":"ICLR"},{"key":"ref70","article-title":"Diffusion2: Dynamic 3D content generation via score composition of video and multi-view diffusion models","author":"Yang","year":"2025","journal-title":"ICLR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00027"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref73","article-title":"4DGen: Grounded 4D content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"4Real: Towards photorealistic 4D scene generation via video diffusion models","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_10"},{"key":"ref77","article-title":"4Diffusion: Multi-view video diffusion model for 4D generation","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref79","article-title":"Animate124: Animating one image to 4D dynamic scene","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"GenXD: Generating any 3D and 4D scenes","author":"Zhao","year":"2025","journal-title":"ICLR"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00441"},{"key":"ref82","article-title":"AR4D: Autoregressive 4D generation from monocular videos","author":"Zhu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"}],"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\/11449040.pdf?arnumber=11449040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:11Z","timestamp":1777611851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01231","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}