Papers › DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework

DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework

19 Mar 2025CVPR 2025 1arXiv:2503.14880archive 2025-07-28

Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar Jr., Xiangyang Ji, Xu-Cheng Yin

Optical flow estimation is essential for video processing tasks, such as restoration and action recognition. The quality of videos is constantly increasing, with current standards reaching 8K resolution. However, optical flow methods are usually designed for low resolution and do not generalize to large inputs due to their rigid architectures. They adopt downscaling or input tiling to reduce the input size, causing a loss of details and global information. There is also a lack of optical flow benchmarks to judge the actual performance of existing methods on high-resolution samples. Previous works only conducted qualitative high-resolution evaluations on hand-picked samples. This paper fills this gap in optical flow estimation in two ways. We propose DPFlow, an adaptive optical flow architecture capable of generalizing up to 8K resolution inputs while trained with only low-resolution samples. We also introduce Kubric-NK, a new benchmark for evaluating optical flow methods with input resolutions ranging from 1K to 8K. Our high-resolution evaluation pushes the boundaries of existing methods and reveals new insights about their generalization capabilities. Extensive experimental results show that DPFlow achieves state-of-the-art results on the MPI-Sintel, KITTI 2015, Spring, and other high-resolution benchmarks.

PaperPDFConference PDFCode

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

Code

hmorimitsu/ptlflow 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

Action RecognitionOptical Flow Estimation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2015 DPFlow Fl-all 3.56 #3 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 DPFlow Fl-fg 4.93 #3 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 (train) DPFlow EPE 3.37 #2 of 19 Archive leaderboard report
Optical Flow Estimation KITTI 2015 (train) DPFlow F1-all 11.1 #2 of 19 Archive leaderboard report
Optical Flow Estimation Sintel-clean DPFlow Average End-Point Error 1.046 #3 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-final DPFlow Average End-Point Error 1.975 #2 of 28 Archive leaderboard report
Optical Flow Estimation Spring DPFlow 1px total 3.442 #2 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

ADOPT

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