Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312445951> ?p ?o ?g. }
- W4312445951 endingPage "266" @default.
- W4312445951 startingPage "250" @default.
- W4312445951 abstract "We present a frame interpolation algorithm that synthesizes an engaging slow-motion video from near-duplicate photos which often exhibit large scene motion. Near-duplicates interpolation is an interesting new application, but large motion poses challenges to existing methods. To address this issue, we adapt a feature extractor that shares weights across the scales, and present a “scale-agnostic” motion estimator. It relies on the intuition that large motion at finer scales should be similar to small motion at coarser scales, which boosts the number of available pixels for large motion supervision. To inpaint wide disocclusions caused by large motion and synthesize crisp frames, we propose to optimize our network with the Gram matrix loss that measures the correlation difference between features. To simplify the training process, we further propose a unified single-network approach that removes the reliance on additional optical-flow or depth network and is trainable from frame triplets alone. Our approach outperforms state-of-the-art methods on the Xiph large motion benchmark while performing favorably on Vimeo-90K, Middlebury and UCF101. Source codes and pre-trained models are available at https://film-net.github.io ." @default.
- W4312445951 created "2023-01-04" @default.
- W4312445951 creator A5006447679 @default.
- W4312445951 creator A5011858791 @default.
- W4312445951 creator A5044231615 @default.
- W4312445951 creator A5063085293 @default.
- W4312445951 creator A5065761531 @default.
- W4312445951 creator A5086604282 @default.
- W4312445951 date "2022-01-01" @default.
- W4312445951 modified "2023-09-30" @default.
- W4312445951 title "FILM: Frame Interpolation for Large Motion" @default.
- W4312445951 cites W1901129140 @default.
- W4312445951 cites W2147253850 @default.
- W4312445951 cites W2470139095 @default.
- W4312445951 cites W2475287302 @default.
- W4312445951 cites W2586480386 @default.
- W4312445951 cites W2604329646 @default.
- W4312445951 cites W2768814045 @default.
- W4312445951 cites W2798365772 @default.
- W4312445951 cites W2894961607 @default.
- W4312445951 cites W2904829482 @default.
- W4312445951 cites W2949258649 @default.
- W4312445951 cites W2950533208 @default.
- W4312445951 cites W2963093735 @default.
- W4312445951 cites W2963782415 @default.
- W4312445951 cites W2964251418 @default.
- W4312445951 cites W2972517494 @default.
- W4312445951 cites W2980116241 @default.
- W4312445951 cites W2981362942 @default.
- W4312445951 cites W2984858187 @default.
- W4312445951 cites W3034921716 @default.
- W4312445951 cites W3035236663 @default.
- W4312445951 cites W3035239272 @default.
- W4312445951 cites W3102015846 @default.
- W4312445951 cites W3108228673 @default.
- W4312445951 cites W3110612869 @default.
- W4312445951 cites W3118401715 @default.
- W4312445951 cites W3168286621 @default.
- W4312445951 cites W3203041407 @default.
- W4312445951 cites W4214626557 @default.
- W4312445951 cites W845365781 @default.
- W4312445951 doi "https://doi.org/10.1007/978-3-031-20071-7_15" @default.
- W4312445951 hasPublicationYear "2022" @default.
- W4312445951 type Work @default.
- W4312445951 citedByCount "12" @default.
- W4312445951 countsByYear W43124459512022 @default.
- W4312445951 countsByYear W43124459512023 @default.
- W4312445951 crossrefType "book-chapter" @default.
- W4312445951 hasAuthorship W4312445951A5006447679 @default.
- W4312445951 hasAuthorship W4312445951A5011858791 @default.
- W4312445951 hasAuthorship W4312445951A5044231615 @default.
- W4312445951 hasAuthorship W4312445951A5063085293 @default.
- W4312445951 hasAuthorship W4312445951A5065761531 @default.
- W4312445951 hasAuthorship W4312445951A5086604282 @default.
- W4312445951 hasBestOaLocation W43124459512 @default.
- W4312445951 hasConcept C10161872 @default.
- W4312445951 hasConcept C104114177 @default.
- W4312445951 hasConcept C11413529 @default.
- W4312445951 hasConcept C115961682 @default.
- W4312445951 hasConcept C126042441 @default.
- W4312445951 hasConcept C13280743 @default.
- W4312445951 hasConcept C137800194 @default.
- W4312445951 hasConcept C138885662 @default.
- W4312445951 hasConcept C146159030 @default.
- W4312445951 hasConcept C154945302 @default.
- W4312445951 hasConcept C155542232 @default.
- W4312445951 hasConcept C167510206 @default.
- W4312445951 hasConcept C174493125 @default.
- W4312445951 hasConcept C185798385 @default.
- W4312445951 hasConcept C202474056 @default.
- W4312445951 hasConcept C205649164 @default.
- W4312445951 hasConcept C2776401178 @default.
- W4312445951 hasConcept C31972630 @default.
- W4312445951 hasConcept C41008148 @default.
- W4312445951 hasConcept C41895202 @default.
- W4312445951 hasConcept C65483669 @default.
- W4312445951 hasConcept C72560505 @default.
- W4312445951 hasConcept C76155785 @default.
- W4312445951 hasConceptScore W4312445951C10161872 @default.
- W4312445951 hasConceptScore W4312445951C104114177 @default.
- W4312445951 hasConceptScore W4312445951C11413529 @default.
- W4312445951 hasConceptScore W4312445951C115961682 @default.
- W4312445951 hasConceptScore W4312445951C126042441 @default.
- W4312445951 hasConceptScore W4312445951C13280743 @default.
- W4312445951 hasConceptScore W4312445951C137800194 @default.
- W4312445951 hasConceptScore W4312445951C138885662 @default.
- W4312445951 hasConceptScore W4312445951C146159030 @default.
- W4312445951 hasConceptScore W4312445951C154945302 @default.
- W4312445951 hasConceptScore W4312445951C155542232 @default.
- W4312445951 hasConceptScore W4312445951C167510206 @default.
- W4312445951 hasConceptScore W4312445951C174493125 @default.
- W4312445951 hasConceptScore W4312445951C185798385 @default.
- W4312445951 hasConceptScore W4312445951C202474056 @default.
- W4312445951 hasConceptScore W4312445951C205649164 @default.
- W4312445951 hasConceptScore W4312445951C2776401178 @default.
- W4312445951 hasConceptScore W4312445951C31972630 @default.
- W4312445951 hasConceptScore W4312445951C41008148 @default.
- W4312445951 hasConceptScore W4312445951C41895202 @default.