Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319301042> ?p ?o ?g. }
- W4319301042 abstract "Most modern frame interpolation approaches rely on explicit bidirectional optical flows between adjacent frames, thus are sensitive to the accuracy of underlying flow estimation in handling occlusions while additionally introducing computational bottlenecks unsuitable for efficient deployment. In this work, we propose a flow-free approach that is completely end-to-end trainable for multi-frame video interpolation. Our method, FLAVR, leverages 3D spatio-temporal kernels to directly learn motion properties from unlabeled videos and greatly simplifies the process of training, testing and deploying frame interpolation models. As a result, FLAVR delivers up to 6× speed up compared to the current state-of-the-art methods for multi-frame interpolation while consistently demonstrating superior qualitative and quantitative results compared with prior methods on popular benchmarks including Vimeo-90K, Adobe-240FPS, and GoPro. Finally, we show that frame interpolation is a competitive self-supervised pre-training task for videos via demonstrating various novel applications of FLAVR including action recognition, optical flow estimation, and video object tracking. Code and trained models are provided in the supplementary material." @default.
- W4319301042 created "2023-02-07" @default.
- W4319301042 creator A5016319243 @default.
- W4319301042 creator A5046609009 @default.
- W4319301042 creator A5061446745 @default.
- W4319301042 creator A5066151318 @default.
- W4319301042 date "2023-01-01" @default.
- W4319301042 modified "2023-10-10" @default.
- W4319301042 title "FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation" @default.
- W4319301042 cites W1522734439 @default.
- W4319301042 cites W1905052409 @default.
- W4319301042 cites W1921093919 @default.
- W4319301042 cites W1965004103 @default.
- W4319301042 cites W1998897200 @default.
- W4319301042 cites W2064076387 @default.
- W4319301042 cites W2147253850 @default.
- W4319301042 cites W2150066425 @default.
- W4319301042 cites W219040644 @default.
- W4319301042 cites W2425121537 @default.
- W4319301042 cites W2470139095 @default.
- W4319301042 cites W2535388113 @default.
- W4319301042 cites W2550462002 @default.
- W4319301042 cites W2560474170 @default.
- W4319301042 cites W2560533888 @default.
- W4319301042 cites W2575671312 @default.
- W4319301042 cites W2578257192 @default.
- W4319301042 cites W2586480386 @default.
- W4319301042 cites W2593722617 @default.
- W4319301042 cites W2738579427 @default.
- W4319301042 cites W2752782242 @default.
- W4319301042 cites W2799087757 @default.
- W4319301042 cites W2883429621 @default.
- W4319301042 cites W2904829482 @default.
- W4319301042 cites W2948242301 @default.
- W4319301042 cites W2949258649 @default.
- W4319301042 cites W2949903291 @default.
- W4319301042 cites W2963093735 @default.
- W4319301042 cites W2963155035 @default.
- W4319301042 cites W2963247196 @default.
- W4319301042 cites W2963268050 @default.
- W4319301042 cites W2963483509 @default.
- W4319301042 cites W2963524571 @default.
- W4319301042 cites W2963782415 @default.
- W4319301042 cites W2964037671 @default.
- W4319301042 cites W2964251418 @default.
- W4319301042 cites W2964700958 @default.
- W4319301042 cites W2969667282 @default.
- W4319301042 cites W2984287396 @default.
- W4319301042 cites W2990503944 @default.
- W4319301042 cites W2997150500 @default.
- W4319301042 cites W2998645105 @default.
- W4319301042 cites W3010874390 @default.
- W4319301042 cites W3034921716 @default.
- W4319301042 cites W3035239272 @default.
- W4319301042 cites W3035524453 @default.
- W4319301042 cites W3102015846 @default.
- W4319301042 cites W3107921985 @default.
- W4319301042 cites W3110612869 @default.
- W4319301042 cites W3115964123 @default.
- W4319301042 cites W3145659481 @default.
- W4319301042 cites W3171519093 @default.
- W4319301042 cites W3174138177 @default.
- W4319301042 cites W343636949 @default.
- W4319301042 cites W4312324876 @default.
- W4319301042 cites W4312409473 @default.
- W4319301042 cites W63091017 @default.
- W4319301042 doi "https://doi.org/10.1109/wacv56688.2023.00211" @default.
- W4319301042 hasPublicationYear "2023" @default.
- W4319301042 type Work @default.
- W4319301042 citedByCount "12" @default.
- W4319301042 countsByYear W43193010422023 @default.
- W4319301042 crossrefType "proceedings-article" @default.
- W4319301042 hasAuthorship W4319301042A5016319243 @default.
- W4319301042 hasAuthorship W4319301042A5046609009 @default.
- W4319301042 hasAuthorship W4319301042A5061446745 @default.
- W4319301042 hasAuthorship W4319301042A5066151318 @default.
- W4319301042 hasBestOaLocation W43193010422 @default.
- W4319301042 hasConcept C104114177 @default.
- W4319301042 hasConcept C111919701 @default.
- W4319301042 hasConcept C115961682 @default.
- W4319301042 hasConcept C126042441 @default.
- W4319301042 hasConcept C137800194 @default.
- W4319301042 hasConcept C154945302 @default.
- W4319301042 hasConcept C155542232 @default.
- W4319301042 hasConcept C167510206 @default.
- W4319301042 hasConcept C202474056 @default.
- W4319301042 hasConcept C27405340 @default.
- W4319301042 hasConcept C2781238097 @default.
- W4319301042 hasConcept C31972630 @default.
- W4319301042 hasConcept C3261483 @default.
- W4319301042 hasConcept C41008148 @default.
- W4319301042 hasConcept C72560505 @default.
- W4319301042 hasConcept C76155785 @default.
- W4319301042 hasConcept C9417928 @default.
- W4319301042 hasConcept C98045186 @default.
- W4319301042 hasConceptScore W4319301042C104114177 @default.
- W4319301042 hasConceptScore W4319301042C111919701 @default.
- W4319301042 hasConceptScore W4319301042C115961682 @default.
- W4319301042 hasConceptScore W4319301042C126042441 @default.
- W4319301042 hasConceptScore W4319301042C137800194 @default.