Papers › Flow-edge Guided Video Completion

Flow-edge Guided Video Completion

3 Sep 2020ECCV 2020 8arXiv:2009.01835archive 2025-07-28

Chen Gao, Ayush Saraf, Jia-Bin Huang, Johannes Kopf

We present a new flow-based video completion algorithm. Previous flow completion methods are often unable to retain the sharpness of motion boundaries. Our method first extracts and completes motion edges, and then uses them to guide piecewise-smooth flow completion with sharp edges. Existing methods propagate colors among local flow connections between adjacent frames. However, not all missing regions in a video can be reached in this way because the motion boundaries form impenetrable barriers. Our method alleviates this problem by introducing non-local flow connections to temporally distant frames, enabling propagating video content over motion boundaries. We validate our approach on the DAVIS dataset. Both visual and quantitative results show that our method compares favorably against the state-of-the-art algorithms.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

vt-vl-lab/FGVC officialmentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Video Inpainting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Inpainting DAVIS FGVC Ewarp 0.1586 #4 of 11 Archive leaderboard report
Video Inpainting DAVIS FGVC PSNR 30.80 #4 of 11 Archive leaderboard report
Video Inpainting DAVIS FGVC SSIM 0.9497 #4 of 11 Archive leaderboard report
Video Inpainting DAVIS FGVC VFID 0.165 #4 of 11 Archive leaderboard report
Video Inpainting HQVI (240p) FGVC LPIPS 0.0409 #5 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) FGVC PSNR 28.37 #5 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) FGVC SSIM 0.9383 #5 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) FGVC VFID 0.2436 #5 of 7 Archive leaderboard report
Video Inpainting HQVI (480p) FGVC LPIPS 0.0388 #2 of 4 Archive leaderboard report
Video Inpainting HQVI (480p) FGVC PSNR 28.63 #2 of 4 Archive leaderboard report
Video Inpainting HQVI (480p) FGVC SSIM 0.9433 #2 of 4 Archive leaderboard report
Video Inpainting HQVI (480p) FGVC VFID 0.0470 #2 of 4 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 FGVC Ewarp 0.1022 #8 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 FGVC PSNR 29.67 #8 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 FGVC SSIM 0.9403 #8 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 FGVC VFID 0.064 #8 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections