Papers › Optical Flow Estimation using a Spatial Pyramid Network
Optical Flow Estimation using a Spatial Pyramid Network
Anurag Ranjan, Michael J. Black
We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow estimate and computing an update to the flow. Instead of the standard minimization of an objective function at each pyramid level, we train one deep network per level to compute the flow update. Unlike the recent FlowNet approach, the networks do not need to deal with large motions; these are dealt with by the pyramid. This has several advantages. First, our Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters. This makes it more efficient and appropriate for embedded applications. Second, since the flow at each pyramid level is small (< 1 pixel), a convolutional approach applied to pairs of warped images is appropriate. Third, unlike FlowNet, the learned convolution filters appear similar to classical spatio-temporal filters, giving insight into the method and how to improve it. Our results are more accurate than FlowNet on most standard benchmarks, suggesting a new direction of combining classical flow methods with deep learning.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Dense Pixel Correspondence Estimation | HPatches | SPyNet | Viewpoint I AEPE | 36.94 | #8 of 8 | Archive leaderboard | report |
| Dense Pixel Correspondence Estimation | HPatches | SPyNet | Viewpoint II AEPE | 50.92 | #8 of 8 | Archive leaderboard | report |
| Dense Pixel Correspondence Estimation | HPatches | SPyNet | Viewpoint III AEPE | 54.29 | #8 of 8 | Archive leaderboard | report |
| Dense Pixel Correspondence Estimation | HPatches | SPyNet | Viewpoint IV AEPE | 62.60 | #8 of 8 | Archive leaderboard | report |
| Dense Pixel Correspondence Estimation | HPatches | SPyNet | Viewpoint V AEPE | 72.57 | #8 of 8 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-clean | Spynet | Average End-Point Error | 6.64 | #29 of 29 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-final | Spynet | Average End-Point Error | 8.36 | #28 of 28 | Archive leaderboard | report |
| Optical Flow Estimation | Spring | SPyNet | 1px total | 29.963 | #10 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