Papers › GlueStick: Robust Image Matching by Sticking Points and Lines Together

GlueStick: Robust Image Matching by Sticking Points and Lines Together

4 Apr 2023ICCV 2023 1arXiv:2304.02008archive 2025-07-28

Rémi Pautrat, Iago Suárez, Yifan Yu, Marc Pollefeys, Viktor Larsson

Line segments are powerful features complementary to points. They offer structural cues, robust to drastic viewpoint and illumination changes, and can be present even in texture-less areas. However, describing and matching them is more challenging compared to points due to partial occlusions, lack of texture, or repetitiveness. This paper introduces a new matching paradigm, where points, lines, and their descriptors are unified into a single wireframe structure. We propose GlueStick, a deep matching Graph Neural Network (GNN) that takes two wireframes from different images and leverages the connectivity information between nodes to better glue them together. In addition to the increased efficiency brought by the joint matching, we also demonstrate a large boost of performance when leveraging the complementary nature of these two features in a single architecture. We show that our matching strategy outperforms the state-of-the-art approaches independently matching line segments and points for a wide variety of datasets and tasks. The code is available at https://github.com/cvg/GlueStick.

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 29 code samples harvested from 2 repositories linked to this paper: 20 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 5 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, 9 ran (5 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 15 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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.

cvg/gluestick officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 9 ran (4 instrument-failed) · 5 unverified report
Golbstein/GlueStick-tensorflow tfSyntology: 15 samples, 11 ran (3 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

29 samples harvested: 20 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 9 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.

2ran · violated contract
2ran · our draft was wrong
5ran; the contract check could not run
11ran
9unverified

Licence: 15 of the 29 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. “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.

cvg/gluestick official repository 14 samples, 9 ran (4 instrument-failed) · 5 unverified
AttentionalPropagation gluestick/models/gluestick.py ran MIT (permissive) · 0bf652d5cd14f0d1 · report fixture: returned AttentionalPropagation · level recorded 2026-09-22
EndPtEncoder gluestick/models/gluestick.py ran MIT (permissive) · 0744c1b780ad0b62 · report fixture: returned EndPtEncoder · level recorded 2026-09-22
GNNLayer gluestick/models/gluestick.py ran MIT (permissive) · c8110ff5f4741d3d · report fixture: returned GNNLayer · level recorded 2026-09-22
KeypointEncoder gluestick/models/gluestick.py ran MIT (permissive) · 92f7e8a94de3df6a · report fixture: returned KeypointEncoder · level recorded 2026-09-22
MLP in 375 papers gluestick/models/gluestick.py ran; the contract check could not run (RAISES) MIT (permissive) · 54fd8d988f6f0e09 · report fixture: signature channels:list/1/int, do_bn:bool/0/bool · returned Sequential · level recorded 2026-09-22
MultiHeadedAttention in 38 papers gluestick/models/gluestick.py ran MIT (permissive) · 35811a32bf5387ee · report fixture: returned MultiHeadedAttention · level recorded 2026-09-22
arange_like gluestick/models/gluestick.py ran · our draft was wrong fingerprinted MIT (permissive) · a6e4f5a51c5441d3 · report fixture: signature x:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
log_double_softmax gluestick/models/gluestick.py ran; the contract check could not run (RAISES) MIT (permissive) · 198c0e35a834307d · report fixture: signature scores:Tensor/3/float, bin_score:Tensor/0/float · returned Tensor · level recorded 2026-09-22
normalize_keypoints in 10 papers gluestick/models/gluestick.py ran; the contract check could not run (RAISES) MIT (permissive) · 7a6d49963474000d · report fixture: signature kpts:Tensor/3/float, shape_or_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
AttentionalGNN gluestick/models/gluestick.py unverified MIT (permissive) · 2e1f2c4bc7c2ecd9 · report
BaseModel in 92 papers gluestick/models/gluestick.py unverified MIT (permissive) · d422ebc642067c6e · report
GlueStick gluestick/models/gluestick.py unverified MIT (permissive) · 7edc3e49a3a70c3c · report
LineLayer gluestick/models/gluestick.py unverified MIT (permissive) · 3c20b46867b9cf11 · report
Golbstein/GlueStick-tensorflow community (archive-listed) 15 samples, 11 ran (3 instrument-failed) · 4 unverified
AttentionalPropagation gluestick.py ran no licence file found · pointer only · 8879256fa01366c9 · report fixture: returned AttentionalPropagation · level recorded 2026-09-22
EndPtEncoder gluestick.py ran no licence file found · pointer only · 91eb969dfeb55794 · report fixture: returned EndPtEncoder · level recorded 2026-09-22
GNNLayer gluestick.py ran no licence file found · pointer only · 4094d3ffd7fbc53a · report fixture: returned GNNLayer · level recorded 2026-09-22
KeypointEncoder gluestick.py ran no licence file found · pointer only · 59b08bff5dc85b8f · report fixture: returned KeypointEncoder · level recorded 2026-09-22
LineLayer gluestick.py ran no licence file found · pointer only · 76d2114282e14498 · report fixture: returned LineLayer · level recorded 2026-09-22
MLP in 375 papers gluestick.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 6ee94794a1b527f5 · report fixture: signature channels:list/1/int, do_bn:bool/0/bool · returned Sequential · level recorded 2026-09-22
MultiHeadedAttention in 38 papers gluestick.py ran fingerprinted no licence file found · pointer only · 0d5fe463a1a289eb · report fixture: signature query:EagerTensor/3/float, key:EagerTensor/3/float, value:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
gluestick.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 35ddab8839071886 · report fixture: signature query:EagerTensor/4/float, key:EagerTensor/4/float, value:EagerTensor/4/float · returned tuple · level recorded 2026-09-22
dict_to_dataclass gluestick.py ran · our draft was wrong no licence file found · pointer only · 46fd24631d359569 · report fixture: signature config_dict:dict/0/? · returned Config · level recorded 2026-09-22
gather_like_in_torch gluestick.py ran · violated contract no licence file found · pointer only · 4273e23e924da510 · report fixture: signature indices:EagerTensor/2/int, values:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-22
normalize_keypoints in 10 papers gluestick.py ran · violated contract fingerprinted no licence file found · pointer only · 6c6c724fa54239ed · report fixture: signature kpts:EagerTensor/3/float, h:int/0/int, w:int/0/int · returned EagerTensor · level recorded 2026-09-22
AttentionalGNN gluestick.py unverified no licence file found · pointer only · 7c4811d20047f201 · report
GlueStick gluestick.py unverified no licence file found · pointer only · baf352f0d6611c26 · report
log_double_softmax gluestick.py unverified no licence file found · pointer only · 7e2f151d8d465b17 · report
scatter_mean in 8 papers gluestick.py unverified no licence file found · pointer only · 403889105a73bc9b · 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. 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 GlueStick (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for GlueStick (graph method: GlueStick). 15 bricks; individually on a fixture: 11 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GlueStick entry · level 0 · unverified · baf352f0d6611c26
  2. AttentionalGNN model · level 0 · unverified · 7c4811d20047f201
  3. EndPtEncoder model · level 1 · ran · 91eb969dfeb55794
  4. KeypointEncoder model · level 1 · ran · 59b08bff5dc85b8f
  5. dict_to_dataclass helper · level 1 · ran · our draft was wrong · 46fd24631d359569
  6. gather_like_in_torch helper · level 1 · ran · violated contract · 4273e23e924da510
  7. log_double_softmax helper · level 0 · unverified · 7e2f151d8d465b17
  8. normalize_keypoints helper · level 1 · ran · violated contract · 6c6c724fa54239ed
  9. GNNLayer model · level 1 · ran · 4094d3ffd7fbc53a
  10. LineLayer model · level 1 · ran · 76d2114282e14498
  11. MLP model · level 1 · ran; the contract check could not run (RAISES) · 6ee94794a1b527f5
  12. AttentionalPropagation model · level 1 · ran · 8879256fa01366c9
  13. scatter_mean helper · level 0 · unverified · 403889105a73bc9b
  14. MultiHeadedAttention model · level 1 · ran · 0d5fe463a1a289eb
  15. attention helper · level 1 · ran; the contract check could not run (RAISES) · 35ddab8839071886

harvested Assembly for GlueStick (graph method: GlueStick). 15 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GlueStick entry · level 0 · unverified · 7edc3e49a3a70c3c
  2. AttentionalGNN model · level 0 · unverified · 2e1f2c4bc7c2ecd9
  3. BaseModel helper · level 0 · unverified · d422ebc642067c6e
  4. EndPtEncoder model · level 1 · ran · 0744c1b780ad0b62
  5. KeypointEncoder model · level 1 · ran · 92f7e8a94de3df6a
  6. arange_like helper · level 1 · ran · our draft was wrong · a6e4f5a51c5441d3
  7. log_double_softmax helper · level 1 · ran; the contract check could not run (RAISES) · 198c0e35a834307d
  8. normalize_keypoints helper · level 1 · ran; the contract check could not run (RAISES) · 7a6d49963474000d
  9. GNNLayer model · level 1 · ran · c8110ff5f4741d3d
  10. LineLayer model · level 0 · unverified · 3c20b46867b9cf11
  11. MetaModel helper · level 0 · unverified · 1d1ea14640fc616e
  12. MLP helper · level 1 · ran; the contract check could not run (RAISES) · 54fd8d988f6f0e09
  13. AttentionalPropagation model · level 1 · ran · 0bf652d5cd14f0d1
  14. MultiHeadedAttention model · level 1 · ran · 35811a32bf5387ee
  15. attention helper · level 0 · unverified · 5317c011246420e0

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="2304.02008") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph Neural NetworkPose EstimationVisual LocalizationVisual Place Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Graph Neural Network

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