{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:54Z","timestamp":1777888674538,"version":"3.51.4"},"reference-count":76,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0905104"],"award-info":[{"award-number":["2023YFF0905104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376244"],"award-info":[{"award-number":["62376244"]}],"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\/iccv51701.2025.01352","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14569-14579","source":"Crossref","is-referenced-by-count":0,"title":["LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion"],"prefix":"10.1109","author":[{"given":"Yisu","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenjie","family":"Cao","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaohui","family":"Yu","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianke","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02130"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3687945"},{"key":"ref6","article-title":"Motion-zero: Zero-shot moving object control framework for diffusion-based video generation","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref9","article-title":"Seine: Short-to-long video diffusion model for generative transition and prediction","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref11","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":"ref12","article-title":"I2vcontrol-camera: Precise video camera control with adjustable motion strength","author":"Feng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00220"},{"key":"ref18","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref21","article-title":"Motionmaster: Training-free camera motion transfer for video generation","author":"Teng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00772"},{"key":"ref24","article-title":"Consistent4d: Consistent 360\u00b0 dynamic object generation from monocular video","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang","year":"2024"},{"key":"ref25","first-page":"125879","article-title":"Animate3d: Animating any 3d model with multi-view video diffusion","volume":"37","author":"Jiang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","volume-title":"Kling","year":"2024"},{"key":"ref30","article-title":"Realcam-i2v: Real-world image-tovideo generation with interactive complex camera control","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"ref32","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref34","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref36","article-title":"Sg-i2v: Self-guided trajectory control in image-to-video generation","author":"Namekata","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01217"},{"key":"ref38","article-title":"Global Structure-from-Motion Revisited","volume-title":"European Conference on Computer Vision (ECCV)","author":"Pan","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref40","article-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","first-page":"1828","article-title":"Analytisch-Geometrische Entwicklungen","author":"Pl\u00fccker","journal-title":"GD Baedeker"},{"key":"ref42","volume-title":"Gen-3 alpha","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref45","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 arXiv"},{"key":"ref46","article-title":"Any-to-any generation via composable diffusion","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Tang","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref48","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3668653"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref54","article-title":"Motionbooth: Motion-aware customized text-to-video generation","author":"Jianzong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28429"},{"key":"ref56","article-title":"Customcrafter: Customized video generation with preserving motion and concept composition abilities","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref57","first-page":"331","article-title":"Draganything: Motion control for anything using entity representation","volume-title":"European Conference on Computer Vision","author":"Weijia","year":"2024"},{"key":"ref58","article-title":"Ifadapter: Instance feature control for grounded text-to-image generation","author":"Yinwei","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref60","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Dejia","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref62","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3633153"},{"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","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref67","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref68","article-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref69","article-title":"Efficient video diffusion models via content-frame motion-latent decomposition","author":"Sihyun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","article-title":"Viewcrafter: Taming video diffusion models for high-fidelity novel view synthesis","author":"Wangbo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref72","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref74","article-title":"Cami2v: Camera-controlled image-to-video diffusion model","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref75","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref76","article-title":"Multi-lora composition for image generation","author":"Zhong","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11444667.pdf?arnumber=11444667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:58Z","timestamp":1777611238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01352","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}