Papers › Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
Morimitsu, Henrique; Zhu, Xiaobin; Ji, Xiangyang; Yin, Xu-Cheng
Optical flow estimation is a challenging task consisting of predicting per-pixel motion vectors between images. Recent methods have employed larger and more complex models to improve the estimation accuracy. However, this impacts the widespread adoption of optical flow methods and makes it harder to train more general models since the optical flow data is hard to obtain. This paper proposes a small and efficient model for optical flow estimation. We design a new spatial recurrent encoder that extracts discriminative features at a significantly reduced size. Unlike standard recurrent units, we utilize Partial Kernel Convolution (PKConv) layers to produce variable multi-scale features with a single shared block. We also design efficient Separable Large Kernels (SLK) to capture large context information with low computational cost. Experiments on public benchmarks show that we achieve state-of-the-art generalization performance while requiring significantly fewer parameters and memory than competing methods. Our model ranks first in the Spring benchmark without finetuning, improving the results by over 10% while requiring an order of magnitude fewer FLOPs and over four times less memory than the following published method without finetuning.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Optical Flow Estimation | KITTI 2015 | RPKNet | Fl-all | 4.64 | #5 of 18 | Archive leaderboard | report |
| Optical Flow Estimation | KITTI 2015 | RPKNet | Fl-fg | 4.69 | #5 of 18 | Archive leaderboard | report |
| Optical Flow Estimation | KITTI 2015 (train) | RPKNet | EPE | 3.79 | #4 of 19 | Archive leaderboard | report |
| Optical Flow Estimation | KITTI 2015 (train) | RPKNet | F1-all | 13.0 | #4 of 19 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-clean | RPKNet | Average End-Point Error | 1.315 | #7 of 29 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-final | RPKNet | Average End-Point Error | 2.657 | #9 of 28 | Archive leaderboard | report |
| Optical Flow Estimation | Spring | RPKNet | 1px total | 4.809 | #3 of 11 | 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