{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:27:51Z","timestamp":1780392471545,"version":"3.54.1"},"reference-count":97,"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\/iccv51701.2025.01162","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12502-12513","source":"Crossref","is-referenced-by-count":1,"title":["Gaussian Variation Field Diffusion for High-Fidelity Video-to-4D Synthesis"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaolong","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baining","family":"Guo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01937"},{"key":"ref6","article-title":"Large-vocabulary 3d diffusion model with transformer","author":"Cao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0602"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02475"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"ref17","article-title":"Get3d: A generative model of high quality 3d textured shapes learned from images","author":"Gao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref19","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"3dgen: Triplane latent diffusion for textured mesh generation","author":"Gupta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_26"},{"key":"ref23","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00404"},{"key":"ref26","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle","year":"2021"},{"key":"ref28","article-title":"Consistent4d: Consistent 360 $ deg dynamic object generation from monocular video","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref33","volume-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_7"},{"key":"ref36","article-title":"Gaussianbody: Clothed human reconstruction via 3d gaussian splatting","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Craftsman: High-fidelity mesh generation with 3d native generation and interactive geometry refiner","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00044"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"ref44","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol","year":"2021"},{"key":"ref45","article-title":"Autodecoding latent 3d diffusion models","author":"Ntavelis","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","volume-title":"Video generation models as world simulators","year":"2024"},{"key":"ref47","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02615-z"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref52","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"issue":"2","key":"ref54","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","first-page":"56828","article-title":"L4gm: Large 4d gaussian reconstruction model","volume":"37","author":"Ren","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref62","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"3d generation on imagenet","author":"Skorokhodov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Dreamcraft3d: Hierarchical 3d generation with bootstrapped diffusion prior","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref68","article-title":"Volumediffusion: Flexible text-to-3d generation with efficient volumetric encoder","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","volume-title":"Fvd: A new metric for video generation","author":"Unterthiner","year":"2019"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0728"},{"key":"ref71","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref72","article-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref74","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"abs\/2305.16213","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref76","article-title":"Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling","author":"Wu","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref77","article-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_21"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00209"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02000"},{"key":"ref81","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref82","article-title":"Octfusion: Octreebased diffusion models for 3d shape generation","author":"Xiong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","article-title":"Atlas gaussians diffusion for 3d generation with infinite number of points","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","article-title":"Diffusion 2: Dynamic 3d content generation via score composition of video and multi-view diffusion models","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00443"},{"key":"ref86","article-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_10"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"issue":"4","key":"ref89","first-page":"1","article-title":"3dshape2vecset: A 3d shape representation for neural fields and generative diffusion models","volume":"42","author":"Zhang","year":"2023","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref90","article-title":"Rodinhd: High-fidelity 3d avatar generation with diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref91","article-title":"Gaussiancube: A structured and explicit radiance representation for 3d generative modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0488"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref95","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14602"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3592103"},{"key":"ref98","article-title":"Visual object networks: Image generation with disentangled 3d representations","volume":"31","author":"Zhu","year":"2018","journal-title":"Advances in neural information processing systems"}],"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\/11444275.pdf?arnumber=11444275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:45:03Z","timestamp":1777578303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01162","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}