Papers › GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

16 Sep 2020NeurIPS 2020 12arXiv:2009.07823archive 2025-07-28

Prune Truong, Martin Danelljan, Luc van Gool, Radu Timofte

The feature correlation layer serves as a key neural network module in numerous computer vision problems that involve dense correspondences between image pairs. It predicts a correspondence volume by evaluating dense scalar products between feature vectors extracted from pairs of locations in two images. However, this point-to-point feature comparison is insufficient when disambiguating multiple similar regions in an image, severely affecting the performance of the end task. We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer. The correspondence volume generated by our module is the result of an internal optimization procedure that explicitly accounts for similar regions in the scene. Moreover, our approach is capable of effectively learning spatial matching priors to resolve further matching ambiguities. We analyze our GOCor module in extensive ablative experiments. When integrated into state-of-the-art networks, our approach significantly outperforms the feature correlation layer for the tasks of geometric matching, optical flow, and dense semantic matching. The code and trained models will be made available at github.com/PruneTruong/GOCor.

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 22 code samples: 21 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 22: 18 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: named in the paper: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 20 samples from 1 repository, 16 ran (10 with no instrument failure; 6 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

PruneTruong/GOCor mentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
PruneTruong/GLU-Net mentioned on GitHubpytorchSyntology: 20 samples, 16 ran (6 instrument-failed) · 4 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

22 samples harvested: 18 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 4 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.

7ran · our draft was wrong
11ran
4unverified

Licence: 22 of the 22 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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.

PruneTruong/GOCor named in the paper 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GlobalGOCor GOCor/global_gocor.py ran · metamorphic tier: deterministic licence not identified · pointer only · 25366ffe25c8bc36 · report fixture: returned GlobalGOCor · level recorded 2026-09-22
PruneTruong/GLU-Net community (archive-listed) 20 samples, 16 ran (6 instrument-failed) · 4 unverified
BilinearConvTranspose2d models/our_models/GLUNet.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · d3e35fbe21b2be24 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
CMDTop models/our_models/GLUNet.py ran GPL-3.0 (copyleft) · pointer only · 4474168045aa4fd4 · report fixture: signature x1:Tensor/4/float, x2:Tensor/4/float, x3:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Conv4d models/our_models/GLUNet.py ran GPL-3.0 (copyleft) · pointer only · 62a354f8ea85f74a · report fixture: signature input:Tensor/6/float · returned Tensor · level recorded 2026-09-24
CorrelationVolume models/our_models/GLUNet.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 1f0e92fa0247a8bc · report fixture: signature feature_A:Tensor/4/float, feature_B:Tensor/4/float · returned Tensor · level recorded 2026-09-22
CorrespondenceMapBase models/our_models/GLUNet.py ran GPL-3.0 (copyleft) · pointer only · 3ab7601dd286313f · report fixture: signature x1:Tensor/4/float, x2:Tensor/4/float, x3:NoneType/0/? · returned Tensor · level recorded 2026-09-24
FeatureCorrelation models/our_models/GLUNet.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 795a509a73c8b933 · report fixture: signature feature_source:Tensor/4/float, feature_target:Tensor/4/float · returned Tensor · level recorded 2026-09-22
FeatureL2Norm models/our_models/GLUNet.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · a3f774c099274f5e · report fixture: signature feature:Tensor/2/float · returned Tensor · level recorded 2026-09-22
OpticalFlowEstimator models/our_models/GLUNet.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · 18e6cd02960c2b23 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24
OpticalFlowEstimatorNoDenseConnection models/our_models/GLUNet.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 2874bd730d68f2b1 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
ResNetPyramid models/our_models/GLUNet.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · 60523f6d6d1f6fa4 · report fixture: signature x:Tensor/4/float, quarter_resolution_only:bool/0/bool, eigth_resolution:bool/0/bool · returned list · level recorded 2026-09-24
conv in 178 papers models/our_models/GLUNet.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · ea448b10b84d2017 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-22
conv_blck models/our_models/GLUNet.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 8da443faacf5f51a · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int, bn:bool/0/bool · returned Sequential · level recorded 2026-09-22
conv_head models/our_models/GLUNet.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 21c67fa7347e53dc · report fixture: signature in_channels:int/0/int · returned Conv2d · level recorded 2026-09-22
deconv in 48 papers models/our_models/GLUNet.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · e5cf22998f71a87e · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int · returned ConvTranspose2d · level recorded 2026-09-22
unnormalise_and_convert_mapping_to_flow models/our_models/GLUNet.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · b2bf0025a986b118 · report fixture: signature map:Tensor/4/float · returned Tensor · level recorded 2026-09-22
warp in 27 papers models/our_models/GLUNet.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 9f7160674c91d903 · report fixture: signature x:Tensor/4/float, flo:Tensor/4/float · returned Tensor · level recorded 2026-09-22
GLUNet_model models/our_models/GLUNet.py unverified GPL-3.0 (copyleft) · pointer only · 0ffb01b5e3868007 · report
NeighConsensus models/our_models/GLUNet.py unverified GPL-3.0 (copyleft) · pointer only · 95ad4c0d44741b19 · report
VGGPyramid models/our_models/GLUNet.py unverified GPL-3.0 (copyleft) · pointer only · dc39cc2333935c87 · report
conv4d in 5 papers models/our_models/GLUNet.py unverified GPL-3.0 (copyleft) · pointer only · 8407da62949de1ee · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
predict_flow in 23 papers repository not located ran · our draft was wrong licence of this copy not recorded · c3f23a008d953af5 · report fixture: signature in_planes:int/0/int · returned Conv2d · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for GOCor (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for GOCor (graph method: GOCor). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. GlobalGOCor entry · level 1 · ran · 25366ffe25c8bc36

harvested Assembly for GOCor (graph method: GOCor). 23 bricks; individually on a fixture: 19 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GLUNet_model entry · level 0 · unverified · 0ffb01b5e3868007
  2. BilinearConvTranspose2d helper · level 1 · ran · d3e35fbe21b2be24
  3. CMDTop helper · level 1 · ran · 4474168045aa4fd4
  4. CorrelationVolume helper · level 1 · ran · 1f0e92fa0247a8bc
  5. FeatureCorrelation helper · level 1 · ran · 795a509a73c8b933
  6. FeatureL2Norm helper · level 1 · ran · a3f774c099274f5e
  7. MutualMatching helper · level 1 · ran; the contract check could not run · 6143bd380b5003fc
  8. NeighConsensus helper · level 0 · unverified · 95ad4c0d44741b19
  9. OpticalFlowEstimator helper · level 1 · ran · 18e6cd02960c2b23
  10. OpticalFlowEstimatorNoDenseConnection helper · level 1 · ran · 2874bd730d68f2b1
  11. ResNetPyramid helper · level 1 · ran · 60523f6d6d1f6fa4
  12. VGGPyramid helper · level 0 · unverified · dc39cc2333935c87
  13. conv helper · level 1 · ran · our draft was wrong · ea448b10b84d2017
  14. deconv helper · level 1 · ran · our draft was wrong · e5cf22998f71a87e
  15. predict_flow helper · level 1 · ran · our draft was wrong · c3f23a008d953af5
  16. unnormalise_and_convert_mapping_to_flow helper · level 1 · ran · our draft was wrong · b2bf0025a986b118
  17. warp helper · level 1 · ran · our draft was wrong · 9f7160674c91d903
  18. CorrespondenceMapBase helper · level 1 · ran · 3ab7601dd286313f
  19. conv_blck helper · level 1 · ran · our draft was wrong · 8da443faacf5f51a
  20. conv_head helper · level 1 · ran · our draft was wrong · 21c67fa7347e53dc
  21. featureL2Norm helper · level 1 · ran · honoured contract · cf9656ffec66503c
  22. Conv4d helper · level 1 · ran · 62a354f8ea85f74a
  23. conv4d helper · level 0 · unverified · 8407da62949de1ee

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="2009.07823") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Dense Pixel Correspondence EstimationFeature CorrelationGeometric MatchingOptical Flow Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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