{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T18:10:59Z","timestamp":1791051059421,"version":"4.1.0"},"reference-count":96,"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"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00336454"],"award-info":[{"award-number":["RS-2024-00336454"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01039","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11164-11175","source":"Crossref","is-referenced-by-count":7,"title":["Reangle-A-Video: 4D Video Generation as Video-to-Video Translation"],"prefix":"10.1109","author":[{"given":"Hyeonho","family":"Jeong","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suhyeon","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong Chul","family":"Ye","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00566"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02130"},{"key":"ref4","article-title":"Syncammaster: Synchronizing multi-camera video generation from diverse viewpoints","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref6","article-title":"Gs-dit: Advancing video generation with pseudo 4d gaussian fields through efficient dense 3d point tracking","author":"Bian","year":"2025.7","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref9","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3687945"},{"key":"ref13","article-title":"Pixart- $\\alpha$ : Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref15","article-title":"Pixart- $\\delta$ : Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Boosting camera motion control for video diffusion transformers","author":"Cheong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02601"},{"key":"ref18","article-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes","author":"Chung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Flux inpainting controlnet","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref23","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":"ref24","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02117"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref27","article-title":"pexels","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"ref30","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024","journal-title":"arXiv preprint"},{"issue":"2","key":"ref35","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref36","article-title":"Symbolic music generation with non-differentiable rule guided diffusion","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Vbench++: Comprehensive and versatile benchmark suite for video generative models","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_21"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00682"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref42","article-title":"Free 2 guide: Gradient-free path integral control for enhancing text-tovideo generation with large vision-language models","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"16240","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","volume":"37","author":"Kuang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","article-title":"Flowedit: Inversion-free text-based editing using pre-trained flow models","author":"Kulikov","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Tweediemix: Improving multi-concept fusion for diffusion-based image\/video generation","author":"Kwon","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Flux","year":"2024"},{"key":"ref50","article-title":"Vivid-zoo: Multi-view video generation with diffusion model","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Realcam-i2v: Real-world image-tovideo generation with interactive complex camera control","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"I","year":"2017","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32685"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref57","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024"},{"key":"ref58","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00065"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref61","article-title":"Low-rank adaptation for fast text-to-image diffusion fine-tuning","volume":"3","author":"Ryu","year":"2023","journal-title":"Low-rank adaptation for fast text-to-image diffusion fine-tuning"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1201\/9781315382555"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1713"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3687980"},{"key":"ref65","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref66","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref67","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":"ref68","article-title":"Towards accurate generative models of video: A new metric \\& challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01651"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref75","article-title":"Controlling space and time with diffusion models","author":"Watson","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Dreamvideo-2: Zero-shot subjectdriven video customization with precise motion control","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02427"},{"key":"ref78","article-title":"Trajectory attention for fine-grained video motion control","author":"Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"Cavia: Camera-controllable multi-view video diffusion with view-integrated attention","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref82","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref84","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref86","article-title":"Training-free diffusion model alignment with sampling demons","author":"Yeh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref87","article-title":"Nvs-solver: Video diffusion model as zero-shot novel view synthesizer","author":"You","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00197"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref94","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref96","article-title":"Videomv: Consistent multi-view generation based on large video generative model","author":"Zuo","year":"2024","journal-title":"arXiv preprint"}],"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\/11445835.pdf?arnumber=11445835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:15Z","timestamp":1777611435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01039","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}