Papers › FeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation

FeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation

1 Jun 2020CVPR 2020 6archive 2025-07-28

Shurui Gui, Chaoyue Wang, Qihua Chen, Dacheng Tao

Video interpolation aims to synthesize non-existent frames between two consecutive frames. Although existing optical flow based methods have achieved promising results, they still face great challenges in dealing with the interpolation of complicated dynamic scenes, which include occlusion, blur or abrupt brightness change. This is mainly because these cases may break the basic assumptions of the optical flow estimation (i.e. smoothness, consistency). In this work, we devised a novel structure-to-texture generation framework which splits the video interpolation task into two stages: structure-guided interpolation and texture refinement. In the first stage, deep structure-aware features are employed to predict feature flows from two consecutive frames to their intermediate result, and further generate the structure image of the intermediate frame. In the second stage, based on the generated coarse result, a Frame Texture Compensator is trained to fill in detailed textures. To the best of our knowledge, this is the first work that attempts to directly generate the intermediate frame through blending deep features. Experiments on both the benchmark datasets and challenging occlusion cases demonstrate the superiority of the proposed framework over the state-of-the-art methods. Codes are available on https://github.com/CM-BF/FeatureFlow.

PaperPDFCode

Code

CM-BF/FeatureFlow officialmentioned in paperpytorch 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

Optical Flow EstimationTexture SynthesisVideo Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation MSU Video Frame Interpolation FeFlow_f LPIPS 0.060 #21 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow_f MS-SSIM 0.911 #21 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow_f PSNR 24.48 #21 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow_f SSIM 0.902 #21 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow_f VMAF 60.70 #21 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow LPIPS 0.070 #23 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow MS-SSIM 0.894 #23 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow PSNR 23.28 #23 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow SSIM 0.889 #23 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FeFlow VMAF 58.11 #23 of 24 Archive leaderboard report
Video Frame Interpolation X4K1000FPS FeFlow_f PSNR 25.16 #18 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS FeFlow_f SSIM 0.783 #18 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS FeFlow_f tOF 6.54 #18 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS FeFlow PSNR 24.00 #19 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS FeFlow SSIM 0.756 #19 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS FeFlow tOF 6.59 #19 of 20 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