Papers › Deep Bayesian Video Frame Interpolation

Deep Bayesian Video Frame Interpolation

23 Oct 2022Conference 2022 10archive 2025-07-28

ZHIYANG YU, Yu Zhang, Xujie Xiang, Dongqing Zou, Xijun Chen, Jimmy S. Ren

Abstract. We present deep Bayesian video frame interpolation, a novel approach for upsampling a low frame-rate video temporally to its higher frame-rate counterpart. Our approach learns posterior distributions of optical flows and frames to be interpolated, which is optimized via learned gradient descent for fast convergence. Each learned step is a lightweight network manipulating gradients of the log-likelihood of estimated frames and flows. Such gradients, parameterized either explicitly or implicitly, model the fidelity of current estimations when matching real image and flow distributions to explain the input observations. With this approach we show new records on 8 of 10 benchmarks, using an architecture with half the parameters of the state-of-the-art model.

PaperPDFCode

Code

Oceanlib/DBVI mentioned in paperpytorchMIT 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 Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation DAVIS DBVI PSNR 28.61 #1 of 2 Archive leaderboard report
Video Frame Interpolation DAVIS DBVI SSIM 0.905 #1 of 2 Archive leaderboard report
Video Frame Interpolation GoPro DBVI PSNR 31.73 #1 of 2 Archive leaderboard report
Video Frame Interpolation GoPro DBVI SSIM 0.947 #1 of 2 Archive leaderboard report
Video Frame Interpolation SNU-FILM (easy) DBVI PSNR 40.46 #3 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (easy) DBVI SSIM 0.991 #3 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) DBVI PSNR 25.90 #1 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) DBVI SSIM 0.876 #1 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) DBVI PSNR 31.68 #2 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) DBVI SSIM 0.953 #2 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) DBVI PSNR 36.95 #2 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) DBVI SSIM 0.985 #2 of 8 Archive leaderboard report
Video Frame Interpolation X4K1000FPS DBVI PSNR 32.89 #2 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS DBVI SSIM 0.939 #2 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