{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T22:07:13Z","timestamp":1776204433850,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730598","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:42:43Z","timestamp":1753260163000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Controllable Tracking-Based Video Frame Interpolation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4012-6292","authenticated-orcid":false,"given":"Karlis Martins","family":"Briedis","sequence":"first","affiliation":[{"name":"DisneyResearch|Studios, Zurich, Switzerland and ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0727-1247","authenticated-orcid":false,"given":"Abdelaziz","family":"Djelouah","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7437-3198","authenticated-orcid":false,"given":"Rapha\u00ebl","family":"Ortiz","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9324-779X","authenticated-orcid":false,"given":"Markus","family":"Gross","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios, Z\u00fcrich, Switzerland and ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1473-1878","authenticated-orcid":false,"given":"Christopher","family":"Schroers","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios, Z\u00fcrich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Simon Baker Daniel Scharstein JP Lewis Stefan Roth Michael\u00a0J Black and Richard Szeliski. 2011. A Database and Evaluation Methodology for Optical Flow. International journal of computer vision 92 1 (2011) 1\u201331.","DOI":"10.1007\/s11263-010-0390-2"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00382"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Karlis\u00a0Martins Briedis Abdelaziz Djelouah Mark Meyer Ian McGonigal Markus Gross and Christopher Schroers. 2021. Neural Frame Interpolation for Rendered Content. ACM Transactions on Graphics 40 6 (Dec. 2021) 239:1\u2013239:13. https:\/\/doi.org\/10.1145\/3478513.3480553","DOI":"10.1145\/3478513.3480553"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"R. Castagno P. Haavisto and G. Ramponi. 1996. A Method for Motion Adaptive Frame Rate Up-Conversion. IEEE Transactions on Circuits and Systems for Video Technology 6 5 (Oct. 1996) 436\u2013446. https:\/\/doi.org\/10.1109\/76.538926","DOI":"10.1109\/76.538926"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00064"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6693"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00351"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Duolikun Danier Fan Zhang and David Bull. 2024. LDMVFI: Video Frame Interpolation with Latent Diffusion Models. Proceedings of the AAAI Conference on Artificial Intelligence 38 2 (March 2024) 1472\u20131480. https:\/\/doi.org\/10.1609\/aaai.v38i2.27912","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Jiong Dong Kaoru Ota and Mianxiong Dong. 2023. Video Frame Interpolation: A Comprehensive Survey. ACM Transactions on Multimedia Computing Communications and Applications 19 2s (May 2023) 78:1\u201378:31. https:\/\/doi.org\/10.1145\/3556544","DOI":"10.1145\/3556544"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.181"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2036"},{"key":"e_1_3_3_2_14_1","volume-title":"International Conference on Learning Representations","author":"Hu Edward\u00a0J","year":"2022","unstructured":"Edward\u00a0J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022b. LoRA: Low-rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00613"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00354"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01831"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00938"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00158"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Nima\u00a0Khademi Kalantari Ting-Chun Wang and Ravi Ramamoorthi. 2016. Learning-Based View Synthesis for Light Field Cameras. ACM Transactions on Graphics 35 6 (Dec. 2016) 193:1\u2013193:10. https:\/\/doi.org\/10.1145\/2980179.2980251","DOI":"10.1145\/2980179.2980251"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00211"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"e_1_3_3_2_25_1","unstructured":"Simon Kiefhaber Simon Niklaus Feng Liu and Simone Schaub-Meyer. 2024. Benchmarking Video Frame Interpolation. https:\/\/doi.org\/10.48550\/arXiv.2403.17128 arxiv:https:\/\/arXiv.org\/abs\/2403.17128\u00a0[cs]"},{"key":"e_1_3_3_2_26_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR)","author":"Kingma Diederik\u00a0P.","year":"2015","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR). San Diego, CA, USA."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00201"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01815"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00536"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01809"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_3"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00352"},{"key":"e_1_3_3_2_34_1","volume-title":"Advances in Neural Information Processing Systems","author":"Luo Grace","year":"2023","unstructured":"Grace Luo, Lisa Dunlap, Dong\u00a0Huk Park, Aleksander Holynski, and Trevor Darrell. 2023. Diffusion Hyperfeatures: Searching through Time and Space for Semantic Correspondence. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_2_35_1","unstructured":"Sourab Mangrulkar Sylvain Gugger Lysandre Debut Younes Belkada Sayak Paul and Benjamin Bossan. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00059"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298747"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00669"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00078"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00183"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"e_1_3_3_2_42_1","first-page":"670","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Niklaus Simon","year":"2017","unstructured":"Simon Niklaus, Long Mai, and Feng Liu. 2017a. Video Frame Interpolation via Adaptive Convolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 670\u2013679."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00157"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_7"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01427"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00946"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01422"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"e_1_3_3_2_53_1","unstructured":"Maham Tanveer Yang Zhou Simon Niklaus Ali\u00a0Mahdavi Amiri Hao Zhang Krishna\u00a0Kumar Singh and Nanxuan Zhao. 2025. MotionBridge: Dynamic Video Inbetweening with Flexible Controls. https:\/\/doi.org\/10.48550\/arXiv.2412.13190 arxiv:https:\/\/arXiv.org\/abs\/2412.13190\u00a0[cs]"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_21"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"e_1_3_3_2_57_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang Wen","year":"2025","unstructured":"Wen Wang, Qiuyu Wang, Kecheng Zheng, Hao OUYANG, Zhekai Chen, Biao Gong, Hao Chen, Yujun Shen, and Chunhua Shen. 2025b. Framer: Interactive Frame Interpolation. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_3_2_58_1","first-page":"0","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Wang Xintao","year":"2018","unstructured":"Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change\u00a0Loy. 2018. ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0\u20130."},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_3"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00266"},{"key":"e_1_3_3_2_61_1","volume-title":"NeurIPS","author":"Xu Xiangyu","year":"2019","unstructured":"Xiangyu Xu, Li Siyao, Wenxiu Sun, Qian Yin, and Ming-Hsuan Yang. 2019. Quadratic Video Interpolation. In NeurIPS."},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"crossref","unstructured":"Tianfan Xue Baian Chen Jiajun Wu Donglai Wei and William\u00a0T Freeman. 2019. Video Enhancement with Task-Oriented Flow. International Journal of Computer Vision (IJCV) 127 8 (2019) 1106\u20131125.","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_3_2_63_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth Anything V2. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"e_1_3_3_2_65_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhang Guozhen","year":"2024","unstructured":"Guozhen Zhang, Chunxu Liu, Yutao Cui, Xiaotong Zhao, Kai Ma, and Limin Wang. 2024b. VFIMamba: Video Frame Interpolation with State Space Models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"e_1_3_3_2_68_1","first-page":"13308","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang Youjian","year":"2020","unstructured":"Youjian Zhang, Chaoyue Wang, and Dacheng Tao. 2020. Video Frame Interpolation without Temporal Priors. In Advances in Neural Information Processing Systems , Vol.\u00a033. Curran Associates, Inc., 13308\u201313318."},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_20"},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02123"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:03:35Z","timestamp":1774019015000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":69,"alternative-id":["10.1145\/3721238.3730598","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730598","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}