{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:44Z","timestamp":1778051504772,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00168","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1674-1684","source":"Crossref","is-referenced-by-count":0,"title":["RapidMV: Leveraging Spatio-Angular Latent Space for Efficient and Consistent Text-to-Multi-View Synthesis"],"prefix":"10.1109","author":[{"given":"Seungwook","family":"Kim","sequence":"first","affiliation":[{"name":"POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichun","family":"Shi","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejie","family":"Li","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Cho","sequence":"additional","affiliation":[{"name":"POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Announcing FLUX1.1 [pro] and the BFL API"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref4","article-title":"Pixart-\\alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref7","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref8","article-title":"Datacomp: In search of the next generation of multimodal datasets","volume":"36","author":"Gadre","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"T3bench: Benchmarking current progress in text-to-3d generation","author":"He","year":"2023"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022"},{"key":"ref12","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01520"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2122"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626363"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01013"},{"key":"ref17","article-title":"Multi-view image prompted multi-view diffusion for improved 3d generation","author":"Kim","year":"2024"},{"key":"ref18","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","article-title":"Open-sora-plan","year":"2024"},{"key":"ref22","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01699"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref25","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref29","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref30","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref33","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref35","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref38","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023"},{"key":"ref39","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref40","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref41","article-title":"Bootstrap3d: Improving 3d content creation with synthetic data","author":"Sun","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref43","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"International Conference on Learning Representations","author":"Villegas"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref45","article-title":"Predicting video with vqvae","author":"Walker","year":"2021"},{"key":"ref46","article-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation","author":"Wang","year":"2023"},{"key":"ref47","article-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","author":"Wang","year":"2021"},{"key":"ref48","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"ref50","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref51","article-title":"Cv-vae: A compatible video vae for latent generative video models","author":"Zhao","year":"2024"},{"key":"ref52","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref53","article-title":"Videomv: Consistent multi-view generation based on large video generative model","author":"Zuo","year":"2024"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491948.pdf?arnumber=11491948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:14:47Z","timestamp":1778048087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00168","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}