{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:14Z","timestamp":1784268674363,"version":"3.55.0"},"reference-count":106,"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\/iccv51701.2025.00017","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"100-111","source":"Crossref","is-referenced-by-count":11,"title":["TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models"],"prefix":"10.1109","author":[{"given":"Mark","family":"Yu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Hu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinbo","family":"Xing","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01594"},{"key":"ref2","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","year":"2025","journal-title":"ICLR"},{"key":"ref3","article-title":"Syncammaster: Synchronizing multi-camera video generation from diverse viewpoints","author":"Bai","year":"2025","journal-title":"ICLR"},{"key":"ref4","article-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref8","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref10","author":"Brooks","journal-title":"Video generation models as world simulators"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"ref13","article-title":"Videocrafter 1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Panda-70m: Captioning 70 m videos with multiple cross-modality teachers","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref16","year":"2024","journal-title":"Cogvideox-fun"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00110"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01121"},{"key":"ref19","author":"Fan","year":"2024","journal-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32299"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2447"},{"key":"ref24","article-title":"Gaussianflow: Splatting gaussian dynamics for 4d content creation","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Fastnerf: High-fidelity neural rendering at 200 fps","author":"Garbin","year":"2021","journal-title":"In ICCV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00832"},{"key":"ref30","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2025","journal-title":"ICLR"},{"key":"ref31","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01811"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00062"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref37","article-title":"kling","year":"2024","journal-title":"kling"},{"key":"ref38","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Fast view synthesis of casual videos with soup-ofplanes","volume-title":"ECCV","author":"Lee","year":"2025"},{"key":"ref40","article-title":"Mosca: Dynamic gaussian fusion from casual videos via 4d motion scaffolds","author":"Lei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref42","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref43","article-title":"Nerfacc: A general nerf acceleration toolbox","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00416"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"ref47","article-title":"Wonderland: Navigating 3d scenes from a single image","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_17"},{"key":"ref49","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657402"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00010"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02125"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00194"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref60","article-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation","author":"Nan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref63","article-title":"Pika","year":"2024","journal-title":"pika"},{"key":"ref64","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref66","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref70","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247082"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687681"},{"key":"ref73","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":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00541"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00789"},{"key":"ref78","article-title":"Shape of motion: 4d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","article-title":"Freevs: Generative view synthesis on free driving trajectory","volume-title":"ICLR","author":"Wang","year":"2025"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref82","author":"Wu","year":"2024","journal-title":"Cat4d: Create anything in 4d with multi-view video diffusion models. arXiv preprint arXiv:2411.18613"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref85","article-title":"Camco: Camera-controllable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00085"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref88","article-title":"Cogvideox: Text-tovideo diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref89","article-title":"Realtime photorealistic dynamic scene representation and rendering with 4d gaussian splatting","author":"Yang","year":"2024","journal-title":"ICLR"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00538"},{"key":"ref91","article-title":"Nvssolver: Video diffusion model as zero-shot novel view synthesizer","author":"You","year":"2025","journal-title":"ICLR"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591555"},{"key":"ref94","article-title":"Evagaussians: Event stream assisted gaussian splatting from blurry images","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_16"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00197"},{"key":"ref99","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_19"},{"key":"ref102","article-title":"Stereocrafter: Diffusion-based generation of long and high-fidelity stereoscopic 3d from monocular videos","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"ref104","article-title":"Holodreamer: Holistic 3d panoramic world generation from text descriptions","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_9"}],"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\/11445093.pdf?arnumber=11445093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:07Z","timestamp":1777611307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00017","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}