Papers › MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

24 Mar 2020CVPR 2020 6arXiv:2003.10955archive 2025-07-28

Shengyu Zhao, Yilun Sheng, Yue Dong, Eric I-Chao Chang, Yan Xu

Feature warping is a core technique in optical flow estimation; however, the ambiguity caused by occluded areas during warping is a major problem that remains unsolved. In this paper, we propose an asymmetric occlusion-aware feature matching module, which can learn a rough occlusion mask that filters useless (occluded) areas immediately after feature warping without any explicit supervision. The proposed module can be easily integrated into end-to-end network architectures and enjoys performance gains while introducing negligible computational cost. The learned occlusion mask can be further fed into a subsequent network cascade with dual feature pyramids with which we achieve state-of-the-art performance. At the time of submission, our method, called MaskFlownet, surpasses all published optical flow methods on the MPI Sintel, KITTI 2012 and 2015 benchmarks. Code is available at https://github.com/microsoft/MaskFlownet.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2003.10955")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: official repository: 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/MaskFlownet officialmentioned in papermentioned on GitHubmxnetMIT report
AMatusV/MaskFlownet-ROS mentioned on GitHubmxnetMIT report
open-mmlab/mmflow pytorchApache-2.0 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

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from microsoft/MaskFlownet. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

build_network microsoft/MaskFlownet/network/pipeline.py official repository unverified MIT (permissive) · 94b4a76fdab01f90 · report
find_checkpoints microsoft/MaskFlownet/path.py official repository unverified MIT (permissive) · c47fe0a72c302ced · report
find_log microsoft/MaskFlownet/path.py official repository unverified MIT (permissive) · dfeb180d90813e96 · report
list_data microsoft/MaskFlownet/reader/sintel.py official repository unverified MIT (permissive) · 27d54fa94eb00588 · report
list_data microsoft/MaskFlownet/reader/things3d.py official repository unverified MIT (permissive) · 4e20def3f316506f · report
load microsoft/MaskFlownet/reader/sintel.py official repository unverified MIT (permissive) · 4acd233d86ecc883 · report
load microsoft/MaskFlownet/reader/things3d.py official repository unverified MIT (permissive) · 90a3966d5dca33d4 · report
read_dataset microsoft/MaskFlownet/reader/hd1k.py official repository unverified MIT (permissive) · 556b925e324756cb · report
read_dataset microsoft/MaskFlownet/reader/kitti.py official repository unverified MIT (permissive) · b822bc9a47b5b34d · report
read_dataset_testing microsoft/MaskFlownet/reader/kitti.py official repository unverified MIT (permissive) · 2f8369aa1ba0c5b8 · report
read_log microsoft/MaskFlownet/path.py official repository unverified MIT (permissive) · 4b09ec7043892f02 · report

Tasks

Optical Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2012 MaskFlownet-S Average End-Point Error 1.1 #2 of 12 Archive leaderboard report
Optical Flow Estimation KITTI 2012 MaskFlownet Average End-Point Error 1.1 #3 of 12 Archive leaderboard report
Optical Flow Estimation KITTI 2015 MaskFlownet Fl-all 6.11 #7 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 MaskFlownet-S Fl-all 6.81 #9 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 (train) MaskFlowNet F1-all 23.1 #14 of 19 Archive leaderboard report
Optical Flow Estimation Sintel-clean MaskFlownet Average End-Point Error 2.52 #14 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-clean MaskFlownet-S Average End-Point Error 2.77 #16 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-final MaskFlownet Average End-Point Error 4.17 #14 of 28 Archive leaderboard report
Optical Flow Estimation Sintel-final MaskFlownet-S Average End-Point Error 4.38 #16 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.

Methods

Introduced by this paper: MaskFlownet

MaskFlownet

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