Papers › AdaLAM: Revisiting Handcrafted Outlier Detection

AdaLAM: Revisiting Handcrafted Outlier Detection

7 Jun 2020arXiv:2006.04250archive 2025-07-28

Luca Cavalli, Viktor Larsson, Martin Ralf Oswald, Torsten Sattler, Marc Pollefeys

Local feature matching is a critical component of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limitations in the descriptors, raw matches are often contaminated by a majority of outliers. As a result, outlier detection is a fundamental problem in computer vision, and a wide range of approaches have been proposed over the last decades. In this paper we revisit handcrafted approaches to outlier filtering. Based on best practices, we propose a hierarchical pipeline for effective outlier detection as well as integrate novel ideas which in sum lead to AdaLAM, an efficient and competitive approach to outlier rejection. AdaLAM is designed to effectively exploit modern parallel hardware, resulting in a very fast, yet very accurate, outlier filter. We validate AdaLAM on multiple large and diverse datasets, and we submit to the Image Matching Challenge (CVPR2020), obtaining competitive results with simple baseline descriptors. We show that AdaLAM is more than competitive to current state of the art, both in terms of efficiency and effectiveness.

PaperPDFCodeCode Syntology ran

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 19 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 19 samples from 3 repositories, 13 ran (13 with no instrument failure; 0 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

antonbrazhnyi/AdaLAM mentioned on GitHubpytorchBSD-3-ClauseSyntology: 9 samples, 4 ran (0 instrument-failed) · 5 unverified report
cavalli1234/AdaLAM mentioned on GitHubpytorchBSD-3-ClauseSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
gujingxiao/BaiduStar2020-Traffic-Sign-Detection-And-Pair-Competition-Solution mentioned on GitHubpaddleApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 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

19 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 6 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.

13ran
6unverified

Licence: 0 of the 19 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 3 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.

antonbrazhnyi/AdaLAM community (archive-listed) 9 samples, 4 ran (0 instrument-failed) · 5 unverified
arange_sequence adalam/utils.py ran BSD-3-Clause (permissive) · 273031afa673ed50 · report fixture: signature ranges:Tensor/1/int · returned Tensor · level recorded 2026-09-24
dist_matrix in 8 papers adalam/utils.py ran fingerprinted BSD-3-Clause (permissive) · a3a952583dcee63e · report fixture: signature d1:Tensor/3/float, d2:Tensor/3/float, is_normalized:bool/0/bool · returned Tensor · level recorded 2026-09-24
orientation_diff adalam/utils.py ran fingerprinted BSD-3-Clause (permissive) · 6e21a7f85e0bd425 · report fixture: signature o1:Tensor/1/float, o2:Tensor/1/float · returned Tensor · level recorded 2026-09-24
select_seeds adalam/core.py ran BSD-3-Clause (permissive) · ce984335a94fc19e · report fixture: signature dist1:Tensor/3/float, R1:Tensor/1/float, scores1:Tensor/2/float, fnn12:Tensor/2/int, mnn:Tensor/2/bool · returned tuple · level recorded 2026-09-24
confidence_based_inlier_selection adalam/ransac.py unverified BSD-3-Clause (permissive) · 0b54a05cf65bbe27 · report
extract_local_patterns adalam/core.py unverified BSD-3-Clause (permissive) · 1baf1bbcafd8baa2 · report
extract_neighborhood_sets adalam/core.py unverified BSD-3-Clause (permissive) · 4c3eec786c61959e · report
group_sum_and_cumsum adalam/ransac.py unverified BSD-3-Clause (permissive) · 6635220d02d11dda · report
stable_sort_residuals adalam/ransac.py unverified BSD-3-Clause (permissive) · 6af9bdca2053ef9c · report
cavalli1234/AdaLAM community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
dist_matrix in 8 papers adalam/utils.py ran fingerprinted BSD-3-Clause (permissive) · 044e5f3c6e44c154 · report fixture: signature d1:Tensor/2/float, d2:Tensor/2/float, is_normalized:bool/0/bool · returned Tensor · level recorded 2026-09-24
extract_local_patterns adalam/core.py ran BSD-3-Clause (permissive) · ccf718aa4ea2a54a · report fixture: signature fnn12:Tensor/1/int, fnn_to_seed_local_consistency_map_corr:Tensor/2/bool, k1:Tensor/2/float, k2:Tensor/2/float, im1seeds:Tensor/1/int, im2seeds:Tensor/1/int, scores:Tensor/1/float · returned tuple · level recorded 2026-09-24
select_seeds adalam/core.py ran BSD-3-Clause (permissive) · ca2ddc97cec6ba7b · report fixture: signature dist1:Tensor/2/float, R1:float/0/float, scores1:Tensor/1/float, fnn12:Tensor/1/int, mnn:Tensor/1/bool · returned tuple · level recorded 2026-09-24
extract_neighborhood_sets adalam/core.py unverified BSD-3-Clause (permissive) · 9e1bd9727a566275 · report
gujingxiao/BaiduStar2020-Traffic-Sign-Detection-And-Pair-Competition-Solution community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
distort_color in 6 papers metric_learning_traffic/imgtool.py ran fingerprinted Apache-2.0 (permissive) · aa62684e7175e3a0 · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-24
generate_index metric_learning_traffic/losses/commonfunc.py ran Apache-2.0 (permissive) · 8934a86d67997100 · report fixture: signature batch_size:int/0/int, samples_each_class:int/0/int · returned ndarray · level recorded 2026-09-24
postprocess in 70 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
PaddleClas/traffic_class_infer.py ran Apache-2.0 (permissive) · 9e2a7fd85f0594c2 · report fixture: signature outputs:list/1/ndarray, topk:int/0/int · returned tuple · level recorded 2026-09-24
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
PaddleClas/traffic_class_infer.py ran Apache-2.0 (permissive) · 63e249d1dde56372 · report fixture: signature data:ndarray/4/float, ops:list/1/callable · returned ndarray · level recorded 2026-09-24
random_crop in 59 papers metric_learning_traffic/imgtool.py ran Apache-2.0 (permissive) · 9b681e8a76479f0f · report fixture: signature img:ndarray/3/int, size:int/0/int, scale:list/1/float, ratio:list/1/float · returned ndarray · level recorded 2026-09-24
rotate_image in 11 papers metric_learning_traffic/imgtool.py ran fingerprinted Apache-2.0 (permissive) · 3668fcd0a8a7ae06 · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-24

Tasks

Key Point MatchingOutlier DetectionVisual Localization

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