Papers › Enhanced Bi-directional Motion Estimation for Video Frame Interpolation

Enhanced Bi-directional Motion Estimation for Video Frame Interpolation

17 Jun 2022arXiv:2206.08572archive 2025-07-28

Xin Jin, Longhai Wu, Guotao Shen, Youxin Chen, Jie Chen, Jayoon Koo, Cheul-hee Hahm

We present a novel simple yet effective algorithm for motion-based video frame interpolation. Existing motion-based interpolation methods typically rely on a pre-trained optical flow model or a U-Net based pyramid network for motion estimation, which either suffer from large model size or limited capacity in handling complex and large motion cases. In this work, by carefully integrating intermediateoriented forward-warping, lightweight feature encoder, and correlation volume into a pyramid recurrent framework, we derive a compact model to simultaneously estimate the bidirectional motion between input frames. It is 15 times smaller in size than PWC-Net, yet enables more reliable and flexible handling of challenging motion cases. Based on estimated bi-directional motion, we forward-warp input frames and their context features to intermediate frame, and employ a synthesis network to estimate the intermediate frame from warped representations. Our method achieves excellent performance on a broad range of video frame interpolation benchmarks. Code and trained models are available at \url{https://github.com/srcn-ivl/EBME}.

PaperPDFCode

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

Code

srcn-ivl/ebme 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 MSU Video Frame Interpolation EBME-H LPIPS 0.024 #7 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME-H MS-SSIM 0.958 #7 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME-H PSNR 28.77 #7 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME-H SSIM 0.931 #7 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME-H VMAF 68.20 #7 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME LPIPS 0.028 #8 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME MS-SSIM 0.957 #8 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME PSNR 28.56 #8 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME SSIM 0.928 #8 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EBME VMAF 69.37 #8 of 24 Archive leaderboard report
Video Frame Interpolation SNU-FILM (easy) EBME-H* PSNR 40.28 #6 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (easy) EBME-H* SSIM 0.9910 #6 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) EBME-H* PSNR 25.40 #8 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) EBME-H* SSIM 0.863 #8 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) EBME-H* PSNR 30.64 #8 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) EBME-H* SSIM 0.937 #8 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) EBME-H* PSNR 36.07 #7 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) EBME-H* SSIM 0.980 #7 of 8 Archive leaderboard report
Video Frame Interpolation UCF101 EBME-H* PSNR 35.41 #7 of 19 Archive leaderboard report
Video Frame Interpolation UCF101 EBME-H* SSIM 0.970 #7 of 19 Archive leaderboard report
Video Frame Interpolation Vimeo90K EBME-H* PSNR 36.19 #6 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K EBME-H* SSIM 0.981 #6 of 23 Archive leaderboard report
Video Frame Interpolation X4K1000FPS EBME-H* PSNR 29.46 #13 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS EBME-H* SSIM 0.902 #13 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.

Methods

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

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