Papers › Many-to-many Splatting for Efficient Video Frame Interpolation

Many-to-many Splatting for Efficient Video Frame Interpolation

7 Apr 2022CVPR 2022 1arXiv:2204.03513archive 2025-07-28

Ping Hu, Simon Niklaus, Stan Sclaroff, Kate Saenko

Motion-based video frame interpolation commonly relies on optical flow to warp pixels from the inputs to the desired interpolation instant. Yet due to the inherent challenges of motion estimation (e.g. occlusions and discontinuities), most state-of-the-art interpolation approaches require subsequent refinement of the warped result to generate satisfying outputs, which drastically decreases the efficiency for multi-frame interpolation. In this work, we propose a fully differentiable Many-to-Many (M2M) splatting framework to interpolate frames efficiently. Specifically, given a frame pair, we estimate multiple bidirectional flows to directly forward warp the pixels to the desired time step, and then fuse any overlapping pixels. In doing so, each source pixel renders multiple target pixels and each target pixel can be synthesized from a larger area of visual context. This establishes a many-to-many splatting scheme with robustness to artifacts like holes. Moreover, for each input frame pair, M2M only performs motion estimation once and has a minuscule computational overhead when interpolating an arbitrary number of in-between frames, hence achieving fast multi-frame interpolation. We conducted extensive experiments to analyze M2M, and found that it significantly improves efficiency while maintaining high effectiveness.

PaperPDFConference PDFCode

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

Code

feinanshan/m2m_vfi officialmentioned in papermentioned on GitHubpytorch 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

Motion EstimationOptical Flow EstimationVideo Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation ATD-12K M2M-PWC PSNR 29.03 #1 of 1 Archive leaderboard report
Video Frame Interpolation ATD-12K M2M-PWC SSIM 0.959 #1 of 1 Archive leaderboard report
Video Frame Interpolation UCF101 M2M-PWC PSNR 35.17 #14 of 19 Archive leaderboard report
Video Frame Interpolation UCF101 M2M-PWC SSIM 0.97 #14 of 19 Archive leaderboard report
Video Frame Interpolation Vimeo90K M2M-PWC PSNR 35.4 #12 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K M2M-PWC SSIM 0.978 #12 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K M2M-PWC Speed (ms/f) 32 (Titan X) #12 of 23 Archive leaderboard report
Video Frame Interpolation X4K1000FPS M2M-PWC PSNR 30.81 #7 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS M2M-PWC SSIM 0.912 #7 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS M2M-PWC Speed (ms/f) 200 (Titan X) #7 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS-2K M2M-PWC PSNR 32.07 #3 of 4 Archive leaderboard report
Video Frame Interpolation X4K1000FPS-2K M2M-PWC SSIM 0.923 #3 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-2K M2M-PWC PSNR 36.45 #4 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-2K M2M-PWC SSIM 0.967 #4 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-4K (Crop) M2M-PWC PSNR 33.93 #1 of 1 Archive leaderboard report
Video Frame Interpolation Xiph-4K (Crop) M2M-PWC SSIM 0.945 #1 of 1 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