Papers › LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

18 Jul 2020ECCV 2020 8arXiv:2007.09319archive 2025-07-28

Tak-Wai Hui, Chen Change Loy

Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. However, the matching problem becomes ill-posed when partially occluded or homogeneous regions exist in images. This causes a cost volume to contain outliers and affects the flow decoding from it. Besides, the coarse-to-fine flow inference demands an accurate flow initialization. Ambiguous correspondence yields erroneous flow fields and affects the flow inferences in subsequent levels. In this paper, we introduce LiteFlowNet3, a deep network consisting of two specialized modules, to address the above challenges. (1) We ameliorate the issue of outliers in the cost volume by amending each cost vector through an adaptive modulation prior to the flow decoding. (2) We further improve the flow accuracy by exploring local flow consistency. To this end, each inaccurate optical flow is replaced with an accurate one from a nearby position through a novel warping of the flow field. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.

PaperPDFConference PDFCode

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

Code

twhui/LiteFlowNet3 officialmentioned in papermentioned on GitHub 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

Optical Flow EstimationScene Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2012 LiteFlowNet3 Average End-Point Error 1.3 #4 of 12 Archive leaderboard report
Optical Flow Estimation KITTI 2012 LiteFlowNet3 Noc 0.7 #4 of 12 Archive leaderboard report
Optical Flow Estimation KITTI 2012 LiteFlowNet3-S Average End-Point Error 1.3 #5 of 12 Archive leaderboard report
Optical Flow Estimation KITTI 2012 LiteFlowNet3-S Noc 0.7 #5 of 12 Archive leaderboard report
Optical Flow Estimation KITTI 2015 LiteFlowNet3-S Fl-all 7.22 #10 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 LiteFlowNet3-S Fl-fg 6.96 #10 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 LiteFlowNet3 Fl-all 7.34 #11 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 LiteFlowNet3 Fl-fg 7.75 #11 of 18 Archive leaderboard report
Optical Flow Estimation Sintel-clean LiteFlowNet3 Average End-Point Error 2.99 #18 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-clean LiteFlowNet3-S Average End-Point Error 3.03 #19 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-final LiteFlowNet3 Average End-Point Error 4.45 #18 of 28 Archive leaderboard report
Optical Flow Estimation Sintel-final LiteFlowNet3-S Average End-Point Error 4.53 #20 of 28 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.

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