Papers › Global Matching with Overlapping Attention for Optical Flow Estimation

Global Matching with Overlapping Attention for Optical Flow Estimation

21 Mar 2022CVPR 2022 1arXiv:2203.11335archive 2025-07-28

Shiyu Zhao, Long Zhao, Zhixing Zhang, Enyu Zhou, Dimitris Metaxas

Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion correspondences and thus cannot handle large motions effectively. In this paper, inspired by the traditional matching-optimization methods where matching is introduced to handle large displacements before energy-based optimizations, we introduce a simple but effective global matching step before the direct regression and develop a learning-based matching-optimization framework, namely GMFlowNet. In GMFlowNet, global matching is efficiently calculated by applying argmax on 4D cost volumes. Additionally, to improve the matching quality, we propose patch-based overlapping attention to extract large context features. Extensive experiments demonstrate that GMFlowNet outperforms RAFT, the most popular optimization-only method, by a large margin and achieves state-of-the-art performance on standard benchmarks. Thanks to the matching and overlapping attention, GMFlowNet obtains major improvements on the predictions for textureless regions and large motions. Our code is made publicly available at https://github.com/xiaofeng94/GMFlowNet

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 7 ran (5 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xiaofeng94/gmflownet officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 7 ran (2 instrument-failed) · 7 unverified 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

14 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
1ran; the contract check could not run
5ran
7unverified

Licence: 0 of the 14 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 xiaofeng94/gmflownet. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

xiaofeng94/gmflownet official repository 14 samples, 7 ran (2 instrument-failed) · 7 unverified
BasicConvEncoder core/gmflownet_model.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 609f6aa177f73bc1 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
BasicMotionEncoder in 10 papers core/gmflownet_model.py ran MIT (permissive) · 782c69df771932e7 · report fixture: signature flow:Tensor/4/float, corr:Tensor/4/float · returned Tensor · level recorded 2026-09-24
CorrBlock in 8 papers core/gmflownet_model.py ran · metamorphic tier: invariant MIT (permissive) · 061bb91459aa0019 · report fixture: signature coords:Tensor/4/float · returned Tensor · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
core/gmflownet_model.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · b20207e9c582c326 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
core/gmflownet_model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · ca7156b5b0317a60 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float · returned tuple · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
core/gmflownet_model.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 0c29759c872834a2 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers core/gmflownet_model.py ran · our draft was wrong MIT (permissive) · 15f7f0358ef0fbda · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
BasicUpdateBlock in 7 papers core/gmflownet_model.py unverified MIT (permissive) · 8025ceaeea5ca5a2 · report
GMFlowNetModel core/gmflownet_model.py unverified MIT (permissive) · 0ae44dff0ca3040c · report
MixAxialPOLABlock core/gmflownet_model.py unverified MIT (permissive) · 61d28a70c06c21d7 · report
MixAxialPOLAUpdate core/gmflownet_model.py unverified MIT (permissive) · 2a65e60045482a36 · report
NeighborWindowAttention core/gmflownet_model.py unverified MIT (permissive) · a189f54d1c241ec9 · report
POLATransBlock core/gmflownet_model.py unverified MIT (permissive) · af3847d6a9584d02 · report
POLAUpdate core/gmflownet_model.py unverified MIT (permissive) · 673740b96395b8cf · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for GMFlowNet (graph method: GMFlowNet). 25 bricks; individually on a fixture: 16 ran (of which 4 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. GMFlowNetModel entry · level 0 · unverified · 0ae44dff0ca3040c
  2. AlternateCorrBlock model · level 0 · unverified · de07f7177a45e51f
  3. BasicConvEncoder helper · level 1 · ran · 609f6aa177f73bc1
  4. BasicEncoder model · level 1 · ran · 89caa833c87120d1
  5. BasicUpdateBlock helper · level 0 · unverified · 8025ceaeea5ca5a2
  6. CorrBlock model · level 1 · ran · 061bb91459aa0019
  7. MixAxialPOLAUpdate helper · level 0 · unverified · 2a65e60045482a36
  8. POLAUpdate helper · level 0 · unverified · 673740b96395b8cf
  9. coords_grid helper · level 1 · ran · honoured contract · 7c8c4c5cb4271dfa
  10. upflow8 helper · level 1 · ran; the contract check could not run · 561d1e8d3102a282
  11. ResidualBlock helper · level 1 · ran · c84b93ca013e3092
  12. BasicMotionEncoder helper · level 1 · ran · 782c69df771932e7
  13. FlowHead helper · level 1 · ran · 919b54dd2d2863a6
  14. SepConvGRU helper · level 1 · ran · 9508f88138c92c66
  15. bilinear_sampler helper · level 0 · unverified · 1ac8cce613d98769
  16. MixAxialPOLABlock helper · level 0 · unverified · 61d28a70c06c21d7
  17. POLATransBlock helper · level 0 · unverified · af3847d6a9584d02
  18. DropPath helper · level 1 · ran · b20207e9c582c326
  19. Mlp helper · level 1 · ran · ab49e7dfb4c6af7e
  20. MultiHeadAttention model · level 1 · ran · ca7156b5b0317a60
  21. NeighborWindowAttention helper · level 0 · unverified · a189f54d1c241ec9
  22. drop_path helper · level 1 · ran; the contract check could not run · 87577b3ff9d32712
  23. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · 0c29759c872834a2
  24. window_reverse helper · level 1 · ran · our draft was wrong · 15f7f0358ef0fbda
  25. _ntuple helper · level 1 · ran · our draft was wrong · 553ee0765abad219

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2203.11335") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Optical Flow Estimationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2015 GMFlowNet Fl-all 4.79 #6 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 GMFlowNet Fl-fg 6.84 #6 of 18 Archive leaderboard report
Optical Flow Estimation KITTI 2015 (train) GMFlowNet EPE 4.24 #6 of 19 Archive leaderboard report
Optical Flow Estimation KITTI 2015 (train) GMFlowNet F1-all 15.4 #6 of 19 Archive leaderboard report
Optical Flow Estimation Sintel-clean GMFlowNet Average End-Point Error 1.390 #9 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-final GMFlowNet Average End-Point Error 2.648 #8 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