Papers › Learning Affine Correspondences by Integrating Geometric Constraints

Learning Affine Correspondences by Integrating Geometric Constraints

7 Apr 2025CVPR 2025 1arXiv:2504.04834archive 2025-07-28

Pengju Sun, Banglei Guan, Zhenbao Yu, Yang Shang, Qifeng Yu, Daniel Barath

Affine correspondences have received significant attention due to their benefits in tasks like image matching and pose estimation. Existing methods for extracting affine correspondences still have many limitations in terms of performance; thus, exploring a new paradigm is crucial. In this paper, we present a new pipeline designed for extracting accurate affine correspondences by integrating dense matching and geometric constraints. Specifically, a novel extraction framework is introduced, with the aid of dense matching and a novel keypoint scale and orientation estimator. For this purpose, we propose loss functions based on geometric constraints, which can effectively improve accuracy by supervising neural networks to learn feature geometry. The experimental show that the accuracy and robustness of our method outperform the existing ones in image matching tasks. To further demonstrate the effectiveness of the proposed method, we applied it to relative pose estimation. Affine correspondences extracted by our method lead to more accurate poses than the baselines on a range of real-world datasets. The code is available at https://github.com/stilcrad/DenseAffine.

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

The archive's official repository (stilcrad/denseaffine) was not harvested; the 13 samples below come from 1 repository the archive does not mark official.

Syntology 13 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 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: found in paper text by Syntology: 13 samples from 1 repository, 8 ran (5 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

stilcrad/denseaffine officialmentioned in paperpytorchSyntology: not harvested 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

13 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 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 · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
2ran
5unverified

Licence: 13 of the 13 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 stilcrad/LearningACs. “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.

stilcrad/LearningACs found in paper text by Syntology 13 samples, 8 ran (3 instrument-failed) · 5 unverified
AffNetFast Network/affine_model.py ran · metamorphic tier: invariant licence not identified · pointer only · a466618f8a546f24 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Unit Network/affine_model.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 2d4ccb2813ab9903 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_norm_xy Network/affine_model.py ran · honoured contract fingerprinted licence not identified · pointer only · bfe32474d1bb04a7 · report fixture: signature xy:ndarray/2/float, row:int/0/int, col:int/0/int · returned ndarray · level recorded 2026-09-22
get_rand_vec Network/affine_model.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 3949f24043ad1382 · report fixture: signature limit:list/1/float, patch_num:int/0/int · returned ndarray · level recorded 2026-09-22
get_trans_mat Network/affine_model.py ran · honoured contract licence not identified · pointer only · a5b38989557ebe9e · report fixture: signature sin_v:float/0/float, cos_v:float/0/float, scale:float/0/float · returned ndarray · level recorded 2026-09-22
make_layers in 155 papers Network/affine_model.py ran · our draft was wrong licence not identified · pointer only · 28a8887902d9d18b · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool, extra_in_channels:int/0/int, nonlinearity:callable/0/?, nonlinearity_kwargs:dict/0/?, co_ord_conv:bool/0/bool · returned Sequential · level recorded 2026-09-22
rectifyAffineTransformationUpIsUp Network/affine_model.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 4cca3e89d39e317a · report fixture: signature A:Tensor/3/float · returned Tensor · level recorded 2026-09-22
to_tensor in 92 papers
census: 8 implementations from 8 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 3, kind float, dtype float32
Network/affine_model.py ran · violated contract fingerprinted licence not identified · pointer only · e7ccfeab258df7aa · report fixture: signature image_np:ndarray/3/float · returned Tensor · level recorded 2026-09-22
AffineModel Network/affine_model.py unverified licence not identified · pointer only · 4dd32fb6112ab6c3 · report
EstiNet Network/affine_model.py unverified licence not identified · pointer only · 59ddc773aeb48965 · report
affine_trans_loss Network/affine_model.py unverified licence not identified · pointer only · a2166abb101c8a2d · report
get_affine_patch Network/affine_model.py unverified licence not identified · pointer only · 7a398b9ad47751d4 · report
get_random_border_point Network/affine_model.py unverified licence not identified · pointer only · 14f41a3c7a624577 · 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 a new pipeline (graph method: a new pipeline). 13 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. AffineModel entry · level 0 · unverified · 4dd32fb6112ab6c3
  2. AffNetFast helper · level 1 · ran · a466618f8a546f24
  3. EstiNet helper · level 0 · unverified · 59ddc773aeb48965
  4. affine_trans_loss loss · level 0 · unverified · a2166abb101c8a2d
  5. rectifyAffineTransformationUpIsUp helper · level 1 · ran; the contract check could not run (RAISES) · 4cca3e89d39e317a
  6. Unit helper · level 1 · ran · 2d4ccb2813ab9903
  7. make_layers helper · level 1 · ran · our draft was wrong · 28a8887902d9d18b
  8. get_affine_patch data_transform · level 0 · unverified · 7a398b9ad47751d4
  9. get_rand_vec helper · level 1 · ran · our draft was wrong · 3949f24043ad1382
  10. get_random_border_point helper · level 0 · unverified · 14f41a3c7a624577
  11. to_tensor helper · level 1 · ran · violated contract · e7ccfeab258df7aa
  12. get_norm_xy helper · level 1 · ran · honoured contract · bfe32474d1bb04a7
  13. get_trans_mat helper · level 1 · ran · honoured contract · a5b38989557ebe9e

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="2504.04834") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Pose Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSoftmax

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