{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:02:41Z","timestamp":1784268161187,"version":"3.55.0"},"reference-count":78,"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\/iccv51701.2025.01241","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13360-13371","source":"Crossref","is-referenced-by-count":3,"title":["I2V3D: Controllable Image-to-Video Generation with 3D Guidance"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"City University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft GenAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"temporal-controlnet-depth-svd-v1","year":"2024"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref7","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","volume-title":"Forty-first International Conference on Machine Learning","author":"Chang","year":"2023"},{"key":"ref8","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes","author":"Chung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_22"},{"key":"ref13","article-title":"I2vcontrol: Disentangled and unified video motion synthesis control","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Scenescape: Text-driven consistent scene generation","author":"Fridman","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref15","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Diffusion as shader: 3daware video diffusion for versatile video generation control","author":"Gu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref18","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00364"},{"key":"ref22","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","volume-title":"Proc.","author":"Karaev","year":"2024"},{"key":"ref23","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. NeurIPS","author":"Karras","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref26","article-title":"Anyv2v: A plug-and-play framework for any video-to-video editing tasks","author":"Ku","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref28","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref29","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"ref31","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Ctrladapter: An efficient and versatile framework for adapting diverse controls to any diffusion model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref34","article-title":"Trailblazer: Trajectory control for diffusion-based video generation","author":"Kurt Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00816"},{"key":"ref37","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Object 3dit: Language-guided 3d-aware image editing","volume":"36","author":"Michel","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"ref40","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref45","article-title":"Zeronvs: Zero-shot 360-degree view synthesis from a single real image","author":"Sargent","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref48","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00067"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref51","article-title":"Triposr: Fast 3d object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref53","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Boximator: Generating rich and controllable motions for video synthesis","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref58","article-title":"Motionctrl: A unified and flexible motion controller for video generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","author":"Zhang","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref60","article-title":"Motionbooth: Motion-aware customized text-to-video generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref62","article-title":"Neural assets: 3d-aware multi-object scene synthesis with image diffusion models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref64","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref68","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00406"},{"key":"ref70","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00555"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref75","article-title":"3ditscene: Editing any scene via language-guided disentangled gaussian splatting","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657403"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185595"}],"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\/11444918.pdf?arnumber=11444918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:48Z","timestamp":1777529988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01241","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}