{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:25:16Z","timestamp":1782318316071,"version":"3.54.5"},"reference-count":75,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306163"],"award-info":[{"award-number":["62306163"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01271","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13695-13706","source":"Crossref","is-referenced-by-count":4,"title":["Dimensionx: Create Any 3D and 4D Scenes From a Single Image With Decoupled Video Diffusion"],"prefix":"10.1109","author":[{"given":"Wenqiang","family":"Sun","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangfu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueqi","family":"Duan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yikai","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref2","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Syncammaster: Synchronizing multi-camera video generation from diverse viewpoints","author":"Bai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref7","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3807511"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3581312"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref13","article-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds","author":"Fan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref22","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref27","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref29","article-title":"Physics3d: Learning physical properties of 3d gaussians via video diffusion","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"ref31","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref33","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"ref35","article-title":"Openvid-1m: A large-scale high-quality dataset for text-to-video generation","author":"Nan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref37","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","article-title":"Zeronvs: Zero-shot 360-degree view synthesis from a single real image","author":"Sargent","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_g09306"},{"key":"ref42","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref45","article-title":"From virtual games to real-world play","author":"Sun","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref47","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01651"},{"key":"ref49","article-title":"Shape of motion: 4 d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_19"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4173"},{"key":"ref53","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref55","article-title":"Controlling space and time with diffusion models","author":"Watson","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref58","article-title":"Unique3d: High-quality and efficient 3d mesh generation from a single image","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0436-y"},{"key":"ref62","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref65","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_15"},{"key":"ref67","article-title":"4real: Towards photorealistic 4d scene generation via video diffusion models","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref68","article-title":"Trajectorycrafter: Redirecting camera trajectory for monocular videos via diffusion models","author":"Mark","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref71","article-title":"Tora: Trajectory-oriented diffusion transformer for video generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref72","article-title":"Riflex: A free lunch for length extrapolation in video diffusion transformers","author":"Zhao","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref73","article-title":"Motiondirector: Motion customization of text-tovideo diffusion models","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref74","article-title":"Animate124: Animating one image to 4d dynamic scene","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref75","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\/11446110.pdf?arnumber=11446110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:22:19Z","timestamp":1777612939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01271","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}