{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:49:06Z","timestamp":1782334146182,"version":"3.54.5"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong Special Administrative Region","award":["ITS\/269\/24FP"],"award-info":[{"award-number":["ITS\/269\/24FP"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tvcg.2026.3687740","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:49:13Z","timestamp":1777319353000},"page":"6738-6750","source":"Crossref","is-referenced-by-count":0,"title":["X2Video: Adapting Diffusion Models for Multimodal Controllable Neural Video Rendering"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6982-4815","authenticated-orcid":false,"given":"Zhitong","family":"Huang","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohan","family":"Zhang","sequence":"additional","affiliation":[{"name":"WeChat, Tencent Inc, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0760-7871","authenticated-orcid":false,"given":"Renhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Manycore Tech Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Tang","sequence":"additional","affiliation":[{"name":"Manycore Tech Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8241-9321","authenticated-orcid":false,"given":"Hao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Manycore Tech Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-5377","authenticated-orcid":false,"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Physically Based Rendering: From Theory to Implementation","author":"Pharr","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","volume":"abs\/2311.15127","author":"Blattmann","year":"2023","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02468"},{"key":"ref5","first-page":"1","article-title":"RGB $\\leftrightarrow$\u2194 x: Image decomposition and synthesis using material- and lighting-aware diffusion models","volume-title":"Proc. ACM SIGGRAPH Conf. Papers","author":"Zeng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02428"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3687910"},{"key":"ref8","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref12","article-title":"Framediffuser: G-buffer-conditioned diffusion for neural forward frame rendering","author":"Beisswenger","year":"2025"},{"key":"ref13","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Yang","year":"2025"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00834","article-title":"Grid diffusion models for text-to-video generation","author":"Lee","year":"2024"},{"key":"ref15","first-page":"34630","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Guo"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref17","article-title":"Open-SORA 2.0: Training a commercial-level video generation model in $200 k","author":"Peng","year":"2025"},{"key":"ref18","article-title":"Kling-omni technical report","author":"Team","year":"2025"},{"key":"ref19","article-title":"Seaweed-7b: Cost-effective training of video generation foundation model","author":"Seawead","year":"2025"},{"key":"ref20","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2025"},{"key":"ref21","article-title":"WAN: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"ref22","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3543687"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3365804"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3568880"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00245"},{"key":"ref27","first-page":"5260","article-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Qiu","year":"2024"},{"key":"ref28","article-title":"Rolling forcing: Autoregressive long video diffusion in real time","volume-title":"Proc. 14th Int. Conf. Learn. Representations","author":"Liu","year":"2026"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2853"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14966"},{"key":"ref32","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hertz"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02294-2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3506992"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555407"},{"key":"ref40","article-title":"InteriorNet: Mega-scale multi-sensor photo-realistic indoor scenes dataset","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Li"},{"key":"ref41","article-title":"Intel open image denoise","author":"\u00c1fra","year":"2025"},{"key":"ref42","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51701.2025.01241","article-title":"I2V3D: Controllable image-to-video generation with 3D guidance","author":"Zhang","year":"2025"},{"key":"ref45","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref46","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref47","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS 2021 Workshop Deep Generative Models Downstream Appl.","author":"Ho"},{"key":"ref48","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref49","article-title":"FVD: A new metric for video generation","volume-title":"Proc. ICLR Workshop DeepGenStruct","author":"Unterthiner"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref52","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11575570\/11494511.pdf?arnumber=11494511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:50:07Z","timestamp":1782330607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11494511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":52,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3687740","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}