{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:54:00Z","timestamp":1777888440036,"version":"3.51.4"},"reference-count":58,"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\/iccv51701.2025.01187","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12779-12789","source":"Crossref","is-referenced-by-count":0,"title":["Latent-Reframe: Enabling Camera Control for Video Diffusion Models Without Training"],"prefix":"10.1109","author":[{"given":"Zhenghong","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"An","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LatentShift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation","author":"An","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"On inductive biases that enable generalization of diffusion transformers","author":"An","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Bring metric functions into diffusion models","author":"An","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","article-title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref9","article-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref12","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref13","article-title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref14","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Imagen Video: High Definition Video Generation with Diffusion Models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Video Diffusion Models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Solving linear inverse problems using the prior implicit in a denoiser","author":"Kadkhodaie","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref23","article-title":"Fifo-diffusion: Generating infinite videos from text without training","author":"Kim","year":"2024","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2025","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref29","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021","journal-title":"ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","article-title":"Accelerating 3d deep learning with pytorch3d","author":"Ravi","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref36","article-title":"Make-A- Video: Text-to-Video Generation without Text-Video Data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref37","article-title":"Splatt3r: Zero-shot gaussian splatting from uncalibrated image pairs","author":"Smart","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref39","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Phenaki: Variable Length Video Generation from Open Domain Textual Description","author":"Villegas","year":"2023","journal-title":"ICLR"},{"key":"ref43","article-title":"MCVD- Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","author":"Voleti","year":"2022","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref45","article-title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","volume-title":"NeurIPS","author":"Wang","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref48","article-title":"Cavia: Camera-controllable multiview video diffusion with view-integrated attention","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Camco: Camera-controllable 3d-consistent image-tovideo generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref52","article-title":"No pose, no problem: Surprisingly simple 3d gaussian splats from sparse unposed images","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Dragnuwa: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00197"},{"key":"ref56","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2025","journal-title":"ICLR"},{"key":"ref57","article-title":"Gooddrag: Towards good practices for drag editing with diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","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\/11443587.pdf?arnumber=11443587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:44:42Z","timestamp":1777610682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01187","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}