{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:52Z","timestamp":1779948112762,"version":"3.53.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00149","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1567-1576","source":"Crossref","is-referenced-by-count":0,"title":["Unlocking the Video Prior for High-Fidelity Sparse Multi-View Image Synthesis"],"prefix":"10.1109","author":[{"given":"Fan","family":"Yang","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Seed,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun Hao","family":"Liew","sequence":"additional","affiliation":[{"name":"ByteDance Seed,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyue","family":"Song","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongcong","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance Seed,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance Seed,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3289752"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381814"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3581312"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2308"},{"key":"ref12","article-title":"3dgen: Triplane latent diffusion for textured mesh generation","author":"Gupta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00908"},{"key":"ref16","article-title":"Era3d: High-resolution multiview diffusion using efficient row-wise attention","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589083"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref19","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref21","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Meshdiffusion: Score-based generative 3d mesh modeling","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref24","article-title":"Point-e: A system for generating 3d point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01314"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref27","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors","author":"Qian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"ref30","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref34","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref38","article-title":"Meshlrm: Large reconstruction model for highquality mesh","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Unique3d: High-quality and efficient 3d mesh generation from a single image","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref41","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Grm: Large gaussian reconstruction model for efficient 3d reconstruction and generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Magic-boost: Boost 3d generation with mutli-view conditioned diffusion","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681634"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref47","article-title":"Videomv: Consistent multi-view generation based on large video generative model","author":"Zuo","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533343.pdf?arnumber=11533343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:03:11Z","timestamp":1779944591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00149","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}