Papers › CDFI: Compression-Driven Network Design for Frame Interpolation

CDFI: Compression-Driven Network Design for Frame Interpolation

18 Mar 2021CVPR 2021 1arXiv:2103.10559archive 2025-07-28

Tianyu Ding, Luming Liang, Zhihui Zhu, Ilya Zharkov

DNN-based frame interpolation--that generates the intermediate frames given two consecutive frames--typically relies on heavy model architectures with a huge number of features, preventing them from being deployed on systems with limited resources, e.g., mobile devices. We propose a compression-driven network design for frame interpolation (CDFI), that leverages model pruning through sparsity-inducing optimization to significantly reduce the model size while achieving superior performance. Concretely, we first compress the recently proposed AdaCoF model and show that a 10X compressed AdaCoF performs similarly as its original counterpart; then we further improve this compressed model by introducing a multi-resolution warping module, which boosts visual consistencies with multi-level details. As a consequence, we achieve a significant performance gain with only a quarter in size compared with the original AdaCoF. Moreover, our model performs favorably against other state-of-the-arts in a broad range of datasets. Finally, the proposed compression-driven framework is generic and can be easily transferred to other DNN-based frame interpolation algorithm. Our source code is available at https://github.com/tding1/CDFI.

PaperPDFConference PDFCode

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

Code

tding1/CDFI 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

Video Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation MSU Video Frame Interpolation CDFI LPIPS 0.051 #17 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation CDFI MS-SSIM 0.926 #17 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation CDFI PSNR 26.99 #17 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation CDFI SSIM 0.908 #17 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation CDFI VMAF 61.72 #17 of 24 Archive leaderboard report
Video Frame Interpolation Middlebury CDFI LPIPS 0.007 #11 of 11 Archive leaderboard report
Video Frame Interpolation Middlebury CDFI PSNR 37.14 #11 of 11 Archive leaderboard report
Video Frame Interpolation Middlebury CDFI SSIM 0.966 #11 of 11 Archive leaderboard report
Video Frame Interpolation UCF101 CDFI LPIPS 0.015 #13 of 19 Archive leaderboard report
Video Frame Interpolation UCF101 CDFI PSNR 35.21 #13 of 19 Archive leaderboard report
Video Frame Interpolation Vimeo90K CDFI LPIPS 0.010 #14 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K CDFI PSNR 35.17 #14 of 23 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

Deformable ConvolutionPruning

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