{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:07Z","timestamp":1783542487440,"version":"3.55.0"},"reference-count":288,"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\/501100002460","name":"Chung-Ang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002460","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-23524035"],"award-info":[{"award-number":["RS-2025-23524035"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["IITP-2024-RS-2024-00418847"],"award-info":[{"award-number":["IITP-2024-RS-2024-00418847"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3672288","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:35Z","timestamp":1773086435000},"page":"9477-9501","source":"Crossref","is-referenced-by-count":5,"title":["AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9233-195X","authenticated-orcid":false,"given":"Dahyeon","family":"Kye","sequence":"first","affiliation":[{"name":"Department of Imaging Science and Arts, GSAIM, Chung-Ang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4043-8848","authenticated-orcid":false,"given":"Changhyun","family":"Roh","sequence":"additional","affiliation":[{"name":"Department of Imaging Science and Arts, GSAIM, Chung-Ang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9772-1735","authenticated-orcid":false,"given":"Sukhun","family":"Ko","sequence":"additional","affiliation":[{"name":"Department of Imaging Science and Arts, GSAIM, Chung-Ang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0623-8074","authenticated-orcid":false,"given":"Chanho","family":"Eom","sequence":"additional","affiliation":[{"name":"Department of Virtual Convergence, GSAIM, Chung-Ang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-0529","authenticated-orcid":false,"given":"Jihyong","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Imaging Science and Arts, GSAIM, Chung-Ang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_18"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.595"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00938"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00382"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00343"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5573\/IEIESPC.2023.12.3.261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00418"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5573\/IEIESPC.2020.9.1.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548163"},{"key":"ref14","article-title":"Coupled video frame interpolation and encoding with hybrid event cameras for low-power high-framerate video","author":"Takahashi","year":"2025","journal-title":"arXiv:2503.22491"},{"key":"ref15","article-title":"Deep multi-scale video prediction beyond mean square error","volume-title":"Proc. ICLR","author":"Mathieu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647865"},{"key":"ref18","first-page":"52220","article-title":"TANGO: Co-speech gesture video reenactment with hierarchical audio motion embedding and diffusion interpolation","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01274"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00515"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_11"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00578"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_14"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327912"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2242631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/30.44281"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/76.305878"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/76.538926"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2002.1037026"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2004.1309458"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.893835"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2007.4429281"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2008.919360"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2010.2043896"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2010.2043895"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2981964"},{"key":"ref37","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. NeurIPS","author":"Jaderberg"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018794"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01246"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00098"},{"key":"ref41","first-page":"1647","article-title":"Quadratic video interpolation","volume-title":"Proc. NeurIPS","author":"Xu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_29"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01422"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00354"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00201"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01427"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_30"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00078"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00157"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00158"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00613"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01831"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2036"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00266"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_20"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887622"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_26"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.244"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00250"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6693"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6634"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3052419"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3100714"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00791"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3075879"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897929"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747182"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00211"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02123"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00183"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2941941"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_7"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00536"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01402"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00114"},{"key":"ref85","article-title":"Frame interpolation with multi-scale deep loss functions and generative adversarial networks","author":"van Amersfoort","year":"2017","journal-title":"arXiv:1711.06045"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2995705"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.015"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3390\/app10186245"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00351"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298747"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00059"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01696"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00352"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3547660"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01809"},{"key":"ref96","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. ICLR","author":"Gu"},{"key":"ref97","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. COLM","author":"Gu"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3405"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01646"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730598"},{"key":"ref101","first-page":"1","article-title":"Boost video frame interpolation via motion adaptation","volume-title":"Proc. BMVC","author":"Wu"},{"key":"ref102","article-title":"Framer: Interactive frame interpolation","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"ref104","article-title":"Beyond boundary frames: Audio-visual semantic guidance for context-aware video interpolation","author":"Deng","year":"2025","journal-title":"arXiv:2512.03590"},{"key":"ref105","article-title":"Arbitrary generative video interpolation","author":"Zhang","year":"2025","journal-title":"arXiv:2510.00578"},{"key":"ref106","article-title":"MultiCOIN: Multi-modal COntrollable video INbetweening","author":"Tanveer","year":"2025","journal-title":"arXiv:2510.08561"},{"key":"ref107","volume-title":"Frame interpolation using generative adversarial networks","author":"Koren","year":"2017"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103434"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867934"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1698"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680846"},{"key":"ref113","first-page":"399","article-title":"DynamiCrafter: Animating open-domain images with video diffusion priors","volume-title":"Proc. ECCV","author":"Xing"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/3687761"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_19"},{"key":"ref116","first-page":"30594","article-title":"Generative inbetweening: Adapting image-to-video models for keyframe interpolation","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref117","first-page":"378","article-title":"Explorative inbetweening of time and space","volume-title":"Proc. ECCV","author":"Fengp"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680961"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02604"},{"key":"ref120","first-page":"3441","article-title":"ViBiDSampler: Enhancing video interpolation using bidirectional diffusion sampler","volume-title":"Proc. ICLR","author":"Yang"},{"key":"ref121","article-title":"Motion-aware generative frame interpolation","author":"Zhang","year":"2025","journal-title":"arXiv:2501.03699"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00202"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02136"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32404"},{"key":"ref125","article-title":"UniPaint: Unified space-time video inpainting via mixture-of-experts","author":"Wan","year":"2024","journal-title":"arXiv:2412.06340"},{"key":"ref126","article-title":"DiffuseSlide: Training-free high frame rate video generation diffusion","author":"Hwang","year":"2025","journal-title":"arXiv:2506.01454"},{"key":"ref127","article-title":"ZeroSmooth: Training-free diffuser adaptation for high frame rate video generation","author":"Yang","year":"2024","journal-title":"arXiv:2406.00908"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01509"},{"key":"ref129","article-title":"EF-VI: Enhancing end-frame injection for video inbetweening","author":"Chen","year":"2025","journal-title":"arXiv:2505.21205"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32486"},{"key":"ref131","article-title":"Controllable human-centric keyframe interpolation with generative prior","author":"Guo","year":"2025","journal-title":"arXiv:2506.03119"},{"key":"ref132","article-title":"Semantic frame interpolation","author":"Hong","year":"2025","journal-title":"arXiv:2507.05173"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-020-02016-y"},{"issue":"2","key":"ref135","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550276","article-title":"Video frame interpolation: A comprehensive survey","volume":"19","author":"Dong","year":"2023","journal-title":"ACM Trans. Multimedia Comput., Commun., Appl."},{"key":"ref136","first-page":"211","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref139","first-page":"1","article-title":"Efficient feature extraction for high-resolution video frame interpolation","volume-title":"Proc. BMVC","author":"Nottebaum"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1981.1094950"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref144","article-title":"LADDER: An efficient framework for video frame interpolation","author":"Shen","year":"2024","journal-title":"arXiv:2404.11108"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3302990"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00502"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/662"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.175"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00936"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00802"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00679"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.181"},{"key":"ref160","first-page":"13308","article-title":"Video frame interpolation without temporal priors","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref161","article-title":"MambaFlow: A mamba-centric architecture for end-to-end optical flow estimation","volume-title":"Proc. CVPR","author":"Du"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01804"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00767"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/18.119725"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1995.537667"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026553619983"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461966"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508376"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486599"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123096"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897364"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref173","first-page":"5769","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. NeurIPS","author":"Gulrajani"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.10717"},{"key":"ref175","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"Proc. ICML","author":"Larsen"},{"key":"ref176","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. ICML","author":"Arjovsky"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5750"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02619"},{"key":"ref182","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref183","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NeurIPS","author":"Dhariwal"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref188","article-title":"I2VGen-XL: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv:2311.04145"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref191","first-page":"83048","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","volume-title":"Proc. ICLR","author":"Yang"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01211"},{"key":"ref193","first-page":"1","article-title":"ConsistI2V: Enhancing visual consistency for image-to-video generation","volume":"2024","author":"Ren","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref194","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref195","first-page":"23694","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. ICLR","author":"Salimans"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref197","article-title":"ControlNeXt: Powerful and efficient control for image and video generation","author":"Peng","year":"2024","journal-title":"arXiv:2408.06070"},{"key":"ref198","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Iclr","author":"Hu"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.33"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00652"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_12"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1994.413553"},{"key":"ref205","first-page":"5992","article-title":"Optimizing the latent space of generative networks","volume-title":"Proc. ICLR","author":"Bojanowski"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0028345"},{"key":"ref208","first-page":"1045","article-title":"OpenVid-1M: A large-scale high-quality dataset for text-to-video generation","volume-title":"Proc. ICLR","author":"Nan"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0916"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0390-2"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01339"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/PCS50896.2021.9477504"},{"key":"ref219","volume-title":"Xiph.org Video Test Media (Derf\u2019s Collection)","author":"Montgomery","year":"1994"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref222","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NeurIPS","author":"Heusel"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018062"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_6"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392457"},{"key":"ref229","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2019","journal-title":"ICLR Workshop"},{"key":"ref230","first-page":"52220","article-title":"Fr\u00e9chet video motion distance: A metric for evaluating motion consistency in videos","volume-title":"Proc. ICML Workshop","author":"Liu"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00532"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_41"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01589"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01432"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01724"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01723"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01728"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_16"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01729"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612093"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00810"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01162"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00414"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2007.914337"},{"key":"ref248","first-page":"4","article-title":"A 2.97 \u03bcm-pitch event-based vision sensor with shared pixel front-end circuitry and low-noise intensity readout mode","volume-title":"IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers","author":"Niwa"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/SIMPAR.2016.7862386"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296630"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/ICCP51581.2021.9466265"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10609864"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00434"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00220"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01695"},{"key":"ref256","article-title":"Time-adaptive video frame interpolation based on residual diffusion","volume-title":"Proc. ACM SIGGRAPH","author":"Chavez"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_17"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3049419"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01011"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01008"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00478"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01079"},{"key":"ref263","article-title":"CPT-interp: Continuous sPatial and temporal motion modeling for 4D medical image interpolation","author":"Li","year":"2024","journal-title":"arXiv:2405.15385"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47969-4_50"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6788"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00293"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00632"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02114"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02608"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3033617"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00516"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_35"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02359"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298849"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_9"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3204753"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3585739"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3510355"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3415415"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01693"},{"key":"ref281","article-title":"DSwinIR: Rethinking window-based attention for image restoration","author":"Wu","year":"2025","journal-title":"arXiv:2504.04869"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02403"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00410"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763904"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00094"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01119"},{"key":"ref287","article-title":"WaterWave: Bridging underwater image enhancement into video streams via wavelet-based temporal consistency field","author":"Zhu","year":"2025","journal-title":"arXiv:2512.05492"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.136"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11427010.pdf?arnumber=11427010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:31Z","timestamp":1783539931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11427010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":288,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3672288","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}