{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:56Z","timestamp":1784228756513,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811109","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4977-757X","authenticated-orcid":false,"given":"Yue","family":"Ma","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, hong kong, COLORADO, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7847-2903","authenticated-orcid":false,"given":"Xu","family":"Ye","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6908-5485","authenticated-orcid":false,"given":"Qinghe","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8378-8221","authenticated-orcid":false,"given":"Yucheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, hong kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4628-6388","authenticated-orcid":false,"given":"Hongyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4680-3151","authenticated-orcid":false,"given":"Yinhan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5492-8015","authenticated-orcid":false,"given":"Xinyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8464-3925","authenticated-orcid":false,"given":"Yuanpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Independent, Hang zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5314-0133","authenticated-orcid":false,"given":"Shanhui","family":"Mo","sequence":"additional","affiliation":[{"name":"Independent, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7768-3610","authenticated-orcid":false,"given":"Paul","family":"Liang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1502-6847","authenticated-orcid":false,"given":"Fangneng","family":"Zhan","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3439-0521","authenticated-orcid":false,"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_1_2_1","unstructured":"2026. Civitai: AI Model Sharing Platform. https:\/\/civitai.com\/models. Accessed: 2026-04-28."},{"key":"e_1_3_3_1_3_1","unstructured":"Niket Agarwal Arslan Ali Maciej Bala Yogesh Balaji Erik Barker Tiffany Cai Prithvijit Chattopadhyay Yongxin Chen Yin Cui Yifan Ding et\u00a0al. 2025. Cosmos world foundation model platform for physical ai. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03575 (2025)."},{"key":"e_1_3_3_1_4_1","unstructured":"Yuxuan Bian Xin Chen Zenan Li Tiancheng Zhi Shen Sang Linjie Luo and Qiang Xu. 2025. Video-As-Prompt: Unified Semantic Control for Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.20888 (2025)."},{"key":"e_1_3_3_1_5_1","unstructured":"Tim Brooks Bill Peebles Connor Holmes Will DePue Yufei Guo Li Jing David Schnurr Joe Taylor Troy Luhman Eric Luhman et\u00a0al. 2024. Video generation models as world simulators. OpenAI Blog 1 8 (2024) 1."},{"key":"e_1_3_3_1_6_1","unstructured":"Zhengcong Fei Debang Li Di Qiu Jiahua Wang Yikun Dou Rui Wang Jingtao Xu Mingyuan Fan Guibin Chen Yang Li et\u00a0al. 2025. Skyreels-a2: Compose anything in video diffusion transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.02436 (2025)."},{"key":"e_1_3_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32304"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00010"},{"key":"e_1_3_3_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681516"},{"key":"e_1_3_3_1_10_1","unstructured":"Jianzhu Guo Dingyun Zhang Xiaoqiang Liu Zhizhou Zhong Yuan Zhang Pengfei Wan and Di Zhang. 2024c. Liveportrait: Efficient portrait animation with stitching and retargeting control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.03168 (2024)."},{"key":"e_1_3_3_1_11_1","first-page":"330","volume-title":"European Conference on Computer Vision","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024b. Sparsectrl: Adding sparse controls to text-to-video diffusion models. In European Conference on Computer Vision. Springer, 330\u2013348."},{"key":"e_1_3_3_1_12_1","unstructured":"Hao He Yinghao Xu Yuwei Guo Gordon Wetzstein Bo Dai Hongsheng Li and Ceyuan Yang. 2024. Cameractrl: Enabling camera control for text-to-video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02101 (2024)."},{"key":"e_1_3_3_1_13_1","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1 2 (2022) 3."},{"key":"e_1_3_3_1_14_1","first-page":"8153","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu Li","year":"2024","unstructured":"Li Hu. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8153\u20138163."},{"key":"e_1_3_3_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01640"},{"key":"e_1_3_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_1_17_1","doi-asserted-by":"crossref","unstructured":"Zeyinzi Jiang Zhen Han Chaojie Mao Jingfeng Zhang Yulin Pan and Yu Liu. 2025. Vace: All-in-one video creation and editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.07598 (2025).","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"e_1_3_3_1_18_1","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6114 (2013)."},{"key":"e_1_3_3_1_19_1","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang et\u00a0al. 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv:https:\/\/arXiv.org\/abs\/2412.03603 (2024)."},{"key":"e_1_3_3_1_20_1","doi-asserted-by":"crossref","unstructured":"Cheng Lei Jiayu Zhang Yue Ma Xinyu Wang Long Chen Liang Tang Yiqiang Yan Fei Su and Zhicheng Zhao. 2025. DiTraj: training-free trajectory control for video diffusion transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.21839 (2025).","DOI":"10.2139\/ssrn.6947474"},{"key":"e_1_3_3_1_21_1","unstructured":"Baolu Li Yiming Zhang Qinghe Wang Liqian Ma Xiaoyu Shi Xintao Wang Pengfei Wan Zhenfei Yin Yunzhi Zhuge Huchuan Lu et\u00a0al. 2025. VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.25772 (2025)."},{"key":"e_1_3_3_1_22_1","unstructured":"Pengyang Ling Jiazi Bu Pan Zhang Xiaoyi Dong Yuhang Zang Tong Wu Huaian Chen Jiaqi Wang and Yi Jin. 2024. Motionclone: Training-free motion cloning for controllable video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.05338 (2024)."},{"key":"e_1_3_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01005"},{"key":"e_1_3_3_1_24_1","unstructured":"Xinyu Liu Ailing Zeng Wei Xue Harry Yang Wenhan Luo Qifeng Liu and Yike Guo. 2025b. VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.05979 (2025)."},{"key":"e_1_3_3_1_25_1","unstructured":"Zeqian Long Mingzhe Zheng Kunyu Feng Xinhua Zhang Hongyu Liu Harry Yang Linfeng Zhang Qifeng Chen and Yue Ma. 2025. Follow-your-shape: Shape-aware image editing via trajectory-guided region control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.08134 (2025)."},{"key":"e_1_3_3_1_26_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 (2017)."},{"key":"e_1_3_3_1_27_1","unstructured":"Yue Ma Kunyu Feng Zhongyuan Hu Xinyu Wang Yucheng Wang Mingzhe Zheng Xuanhua He Chenyang Zhu Hongyu Liu Yingqing He et\u00a0al. 2025a. Controllable video generation: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.16869 (2025)."},{"key":"e_1_3_3_1_28_1","unstructured":"Yue Ma Kunyu Feng Xinhua Zhang Hongyu Liu David\u00a0Junhao Zhang Jinbo Xing Yinhan Zhang Ayden Yang Zeyu Wang and Qifeng Chen. 2025b. Follow-Your-Creation: Empowering 4D Creation through Video Inpainting. arXiv:https:\/\/arXiv.org\/abs\/2506.04590 (2025)."},{"key":"e_1_3_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"e_1_3_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"e_1_3_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"e_1_3_3_1_32_1","unstructured":"Yue Ma Yulong Liu Qiyuan Zhu Ayden Yang Kunyu Feng Xinhua Zhang Zhifeng Li Sirui Han Chenyang Qi and Qifeng Chen. 2025d. Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.05207 (2025)."},{"key":"e_1_3_3_1_33_1","unstructured":"Yue Ma Xinyu Wang Qianli Ma Qinghe Wang Mingzhe Zheng Xiangpeng Yang Hao Li Chongbo Zhao Jixuan Ying Harry Yang et\u00a0al. 2026a. Group Editing: Edit Multiple Images in One Go. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2603.22883 (2026)."},{"key":"e_1_3_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548257"},{"key":"e_1_3_3_1_35_1","unstructured":"Yue Ma Zhikai Wang Tianhao Ren Mingzhe Zheng Hongyu Liu Jiayi Guo Mark Fong Yuxuan Xue Zixiang Zhao Konrad Schindler et\u00a0al. 2026b. FastVMT: Eliminating Redundancy in Video Motion Transfer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.05551 (2026)."},{"key":"e_1_3_3_1_36_1","unstructured":"Yue Ma Zexuan Yan Hongyu Liu Hongfa Wang Heng Pan Yingqing He Junkun Yuan Ailing Zeng Chengfei Cai Heung-Yeung Shum et\u00a0al. 2025e. Follow-your-emoji-faster: Towards efficient fine-controllable and expressive freestyle portrait animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.16630 (2025)."},{"key":"e_1_3_3_1_37_1","unstructured":"Fangyuan Mao Aiming Hao Jintao Chen Dongxia Liu Xiaokun Feng Jiashu Zhu Meiqi Wu Chubin Chen Jiahong Wu and Xiangxiang Chu. 2025. Omni-effects: Unified and spatially-controllable visual effects generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.07981 (2025)."},{"key":"e_1_3_3_1_38_1","unstructured":"Bohao Peng Jian Wang Yuechen Zhang Wenbo Li Ming-Chang Yang and Jiaya Jia. 2024. Controlnext: Powerful and efficient control for image and video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06070 (2024)."},{"key":"e_1_3_3_1_39_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_40_1","unstructured":"Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1701.06538 (2017)."},{"key":"e_1_3_3_1_41_1","unstructured":"Yutao Shen Junkun Yuan Toru Aonishi Hideki Nakayama and Yue Ma. 2025. Follow-Your-Preference: Towards Preference-Aligned Image Inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.23082 (2025)."},{"key":"e_1_3_3_1_42_1","doi-asserted-by":"crossref","unstructured":"Yiren Song Danze Chen and Mike\u00a0Zheng Shou. 2025a. LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01105 (2025).","DOI":"10.1109\/ICCV51701.2025.01835"},{"key":"e_1_3_3_1_43_1","unstructured":"Yiren Song Cheng Liu and Mike\u00a0Zheng Shou. 2025b. MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01572 (2025)."},{"key":"e_1_3_3_1_44_1","unstructured":"Kling Team Jialu Chen Yuanzheng Ci Xiangyu Du Zipeng Feng Kun Gai Sainan Guo Feng Han Jingbin He Kang He et\u00a0al. 2025. Kling-Omni Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.16776 (2025)."},{"key":"e_1_3_3_1_45_1","unstructured":"Boyang Wang Xuweiyi Chen Matheus Gadelha and Zezhou Cheng. 2025a. Frame In-N-Out: Unbounded Controllable Image-to-Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.21491 (2025)."},{"key":"e_1_3_3_1_46_1","unstructured":"Jiangshan Wang Junfu Pu Zhongang Qi Jiayi Guo Yue Ma Nisha Huang Yuxin Chen Xiu Li and Ying Shan. 2024b. Taming rectified flow for inversion and editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.04746 (2024)."},{"key":"e_1_3_3_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01059"},{"key":"e_1_3_3_1_48_1","doi-asserted-by":"crossref","unstructured":"Xiang Wang Shiwei Zhang Changxin Gao Jiayu Wang Xiaoqiang Zhou Yingya Zhang Luxin Yan and Nong Sang. 2025b. Unianimate: Taming unified video diffusion models for consistent human image animation. Science China Information Sciences 68 10 (2025) 1\u201314.","DOI":"10.1007\/s11432-024-4592-3"},{"key":"e_1_3_3_1_49_1","unstructured":"Zhao Wang et\u00a0al. 2024a. Customvideo: Customizing text-to-video generation with multiple subjects. arXiv:https:\/\/arXiv.org\/abs\/2401.09962 (2024)."},{"key":"e_1_3_3_1_50_1","volume-title":"CVPR","author":"Wei Yujie","year":"2024","unstructured":"Yujie Wei et\u00a0al. 2024. Dreamvideo: Composing your dream videos with customized subject and motion. In CVPR."},{"key":"e_1_3_3_1_51_1","first-page":"331","volume-title":"European Conference on Computer Vision","author":"Wu Weijia","year":"2024","unstructured":"Weijia Wu, Zhuang Li, Yuchao Gu, Rui Zhao, Yefei He, David\u00a0Junhao Zhang, Mike\u00a0Zheng Shou, Yan Li, Tingting Gao, and Di Zhang. 2024. Draganything: Motion control for anything using entity representation. In European Conference on Computer Vision. Springer, 331\u2013348."},{"key":"e_1_3_3_1_52_1","doi-asserted-by":"crossref","unstructured":"Jinbo Xing Menghan Xia Yuxin Liu Yuechen Zhang Yong Zhang Yingqing He Hanyuan Liu Haoxin Chen Xiaodong Cun Xintao Wang et\u00a0al. 2024. Make-your-video: Customized video generation using textual and structural guidance. IEEE Transactions on Visualization and Computer Graphics 31 2 (2024) 1526\u20131541.","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"e_1_3_3_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"e_1_3_3_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01623"},{"key":"e_1_3_3_1_55_1","unstructured":"Xiangpeng Yang Ji Xie Yiyuan Yang Yan Huang Min Xu and Qiang Wu. 2025. Unified Video Editing with Temporal Reasoner. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.07469 (2025)."},{"key":"e_1_3_3_1_56_1","unstructured":"Zhuoyi Yang Jiayan Teng et\u00a0al. 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06072 (2024)."},{"key":"e_1_3_3_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01696"},{"key":"e_1_3_3_1_58_1","unstructured":"Bo Yin Xiaobin Hu Xingyu Zhou Peng-Tao Jiang Yue Liao Junwei Zhu Jiangning Zhang Ying Tai Chengjie Wang and Shuicheng Yan. 2025. FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning. arxiv:https:\/\/arXiv.org\/abs\/2511.17979\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2511.17979"},{"key":"e_1_3_3_1_59_1","unstructured":"Xinlei Yu Zhangquan Chen Yongbo He Tianyu Fu Cheng Yang Chengming Xu Yue Ma Xiaobin Hu Zhe Cao Jie Xu et\u00a0al. 2026. The latent space: Foundation evolution mechanism ability and outlook. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2604.02029 (2026)."},{"key":"e_1_3_3_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730683"},{"key":"e_1_3_3_1_61_1","unstructured":"Shiyi Zhang Junhao Zhuang Zhaoyang Zhang Ying Shan and Yansong Tang. 2025d. FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios. arxiv:https:\/\/arXiv.org\/abs\/2505.03730\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2505.03730"},{"key":"e_1_3_3_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"e_1_3_3_1_63_1","doi-asserted-by":"crossref","unstructured":"Yuxuan Zhang Yirui Yuan Yiren Song Haofan Wang and Jiaming Liu. 2025b. Easycontrol: Adding efficient and flexible control for diffusion transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.07027 (2025).","DOI":"10.1109\/ICCV51701.2025.01814"},{"key":"e_1_3_3_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02603"},{"key":"e_1_3_3_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755128"},{"key":"e_1_3_3_1_66_1","first-page":"145","volume-title":"European Conference on Computer Vision","author":"Zhu Shenhao","year":"2024","unstructured":"Shenhao Zhu, Junming\u00a0Leo Chen, Zuozhuo Dai, Zilong Dong, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, and Siyu Zhu. 2024. Champ: Controllable and consistent human image animation with 3d parametric guidance. In European Conference on Computer Vision. Springer, 145\u2013162."},{"key":"e_1_3_3_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611897"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:24:25Z","timestamp":1784226265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":66,"alternative-id":["10.1145\/3799902.3811109","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811109","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}