Papers › ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
Duolikun Danier, Fan Zhang, David Bull
Video frame interpolation (VFI) is currently a very active research topic, with applications spanning computer vision, post production and video encoding. VFI can be extremely challenging, particularly in sequences containing large motions, occlusions or dynamic textures, where existing approaches fail to offer perceptually robust interpolation performance. In this context, we present a novel deep learning based VFI method, ST-MFNet, based on a Spatio-Temporal Multi-Flow architecture. ST-MFNet employs a new multi-scale multi-flow predictor to estimate many-to-one intermediate flows, which are combined with conventional one-to-one optical flows to capture both large and complex motions. In order to enhance interpolation performance for various textures, a 3D CNN is also employed to model the content dynamics over an extended temporal window. Moreover, ST-MFNet has been trained within an ST-GAN framework, which was originally developed for texture synthesis, with the aim of further improving perceptual interpolation quality. Our approach has been comprehensively evaluated -- compared with fourteen state-of-the-art VFI algorithms -- clearly demonstrating that ST-MFNet consistently outperforms these benchmarks on varied and representative test datasets, with significant gains up to 1.09dB in PSNR for cases including large motions and dynamic textures. Project page: https://danielism97.github.io/ST-MFNet.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Frame Interpolation | DAVIS | ST-MFNet | PSNR | 28.287 | #2 of 2 | Archive leaderboard | report |
| Video Frame Interpolation | DAVIS | ST-MFNet | SSIM | 0.895 | #2 of 2 | Archive leaderboard | report |
| Video Frame Interpolation | SNU-FILM (easy) | ST-MFNet | PSNR | 40.775 | #1 of 8 | Archive leaderboard | report |
| Video Frame Interpolation | SNU-FILM (extreme) | ST-MFNet | PSNR | 25.81 | #2 of 8 | Archive leaderboard | report |
| Video Frame Interpolation | SNU-FILM (hard) | ST-MFNet | PSNR | 31.698 | #1 of 8 | Archive leaderboard | report |
| Video Frame Interpolation | SNU-FILM (medium) | ST-MFNet | PSNR | 37.111 | #1 of 8 | Archive leaderboard | report |
| Video Frame Interpolation | UCF101 | ST-MFNet | PSNR | 33.384 | #18 of 19 | Archive leaderboard | report |
| Video Frame Interpolation | VFITex | ST-MFNet | PSNR | 29.175 | #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.
Methods
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