{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:35Z","timestamp":1777888715319,"version":"3.51.4"},"reference-count":93,"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\/iccv51701.2025.02479","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-12","source":"Crossref","is-referenced-by-count":0,"title":["VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling"],"prefix":"10.1109","author":[{"given":"Hyojun","family":"Go","sequence":"first","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byeongjun","family":"Park","sequence":"additional","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyelin","family":"Nam","sequence":"additional","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byung-Hoon","family":"Kim","sequence":"additional","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyungjin","family":"Chung","sequence":"additional","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changick","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2022","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Analyticdpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models","author":"Bao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"International Conference on Machine Learning","author":"Bao","year":"2023"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref12","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Pref3r: Posefree feed-forward 3d gaussian splatting from variable-length image sequence","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes","author":"Chung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref17","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":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1185"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02005"},{"key":"ref21","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_26"},{"key":"ref23","article-title":"T3 bench: Benchmarking current progress in text-to-3d generation","author":"He","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref25","first-page":"30","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref29","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref31","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","volume-title":"Black Forest Labs. Flux","year":"2024"},{"key":"ref33","first-page":"13427","article-title":"Multi-architecture multiexpert diffusion models","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Lee","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00081"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2391"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_16"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00083"},{"key":"ref38","article-title":"Diffsplat: Repurposing image diffusion models for scalable gaussian splat generation","author":"Lin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref42","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref45","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2973"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref53","article-title":"Point-e: A system for generating 3d point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Large language diffusion models","author":"Nie","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_27"},{"key":"ref56","article-title":"Denoising task routing for diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Park","year":"2024"},{"key":"ref57","first-page":"1828","article-title":"Analytisch-geometrische Entwicklungen","author":"Pl\u00fccker","journal-title":"GD Baedeker"},{"key":"ref58","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01759"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00086"},{"key":"ref63","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref64","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref65","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00067"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref68","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang","year":"2024"},{"key":"ref69","volume-title":"Genmo Team. Mochi 1","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0728"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref72","article-title":"Cg3d: Compositional generation for text-to-3d via gaussian splatting","author":"Vilesov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00272"},{"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\/CVPR52733.2024.00649"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00555"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref85","article-title":"Gaussiancube: A structured and explicit radiance representation for 3d generative modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref87","article-title":"Cameras as rays: Pose estimation via ray diffusion","author":"Jason","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"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\/11444601.pdf?arnumber=11444601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:36Z","timestamp":1777611216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02479","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}