Papers › Grounding Image Matching in 3D with MASt3R

Grounding Image Matching in 3D with MASt3R

14 Jun 2024arXiv:2406.09756archive 2025-07-28

Vincent Leroy, Yohann Cabon, Jérôme Revaud

Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to camera pose and scene geometry, it is typically treated as a 2D problem. This makes sense as the goal of matching is to establish correspondences between 2D pixel fields, but also seems like a potentially hazardous choice. In this work, we take a different stance and propose to cast matching as a 3D task with DUSt3R, a recent and powerful 3D reconstruction framework based on Transformers. Based on pointmaps regression, this method displayed impressive robustness in matching views with extreme viewpoint changes, yet with limited accuracy. We aim here to improve the matching capabilities of such an approach while preserving its robustness. We thus propose to augment the DUSt3R network with a new head that outputs dense local features, trained with an additional matching loss. We further address the issue of quadratic complexity of dense matching, which becomes prohibitively slow for downstream applications if not carefully treated. We introduce a fast reciprocal matching scheme that not only accelerates matching by orders of magnitude, but also comes with theoretical guarantees and, lastly, yields improved results. Extensive experiments show that our approach, coined MASt3R, significantly outperforms the state of the art on multiple matching tasks. In particular, it beats the best published methods by 30% (absolute improvement) in VCRE AUC on the extremely challenging Map-free localization dataset.

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 17 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 14 ran (7 with no instrument failure; 7 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.

naver/mast3r officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 17 samples, 14 ran (7 instrument-failed) · 3 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

17 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
3ran; the contract check could not run
7ran
3unverified

Licence: 17 of the 17 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 naver/mast3r. “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.

naver/mast3r official repository 17 samples, 14 ran (7 instrument-failed) · 3 unverified
apply_log_to_norm mast3r/losses.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f3fd659d5f95c771 · report fixture: signature xyz:Tensor/2/float · returned Tensor · level recorded 2026-09-24
batched_triangulate mast3r/cloud_opt/triangulation.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 474afb3f38b2c1bc · report fixture: signature pts2d:Tensor/4/float, proj_mats:Tensor/4/float · returned Tensor · level recorded 2026-09-24
bruteforce_reciprocal_nns mast3r/fast_nn.py ran licence not identified · pointer only · 60d067ba9a3fb4a6 · report fixture: signature A:Tensor/2/float, B:Tensor/2/float, device:str/0/str, block_size:NoneType/0/?, dist:str/0/str · returned tuple · level recorded 2026-09-24
convert_dust3r_pairs_naming mast3r/cloud_opt/sparse_ga.py ran licence not identified · pointer only · f6b7e329975502ed · report fixture: signature imgs:list/1/Tensor, pairs_in:list/1/list · returned list · level recorded 2026-09-24
gamma_loss mast3r/cloud_opt/utils/losses.py ran licence not identified · pointer only · a28441649e04c270 · report fixture: signature gamma:float/0/float, mul:float/0/float, offset:float/0/float, clip:float/0/float · returned function · level recorded 2026-09-24
get_similarities mast3r/losses.py ran fingerprinted no licence file found · pointer only · 6e6b3f8c6d2c3d69 · report fixture: signature desc1:Tensor/3/float, desc2:Tensor/3/float, euc:bool/0/bool · returned Tensor · level recorded 2026-09-24
how_select_local mast3r/retrieval/model.py ran licence not identified · pointer only · eaadf59dfacc29f6 · report fixture: signature feat:Tensor/3/float, attn:Tensor/2/float, nfeat:int/0/int · returned tuple · level recorded 2026-09-24
l05_loss mast3r/cloud_opt/utils/losses.py ran · our draft was wrong fingerprinted licence not identified · pointer only · fdeb9a710048befb · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
l1_loss in 149 papers
census: 3 implementations from 7 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
mast3r/cloud_opt/utils/losses.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 57af2b727ab331be · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
merge_corres mast3r/fast_nn.py ran licence not identified · pointer only · 6575a76869abe3b3 · report fixture: signature idx1:ndarray/1/int, idx2:ndarray/1/int, shape1:tuple/1/int, shape2:tuple/1/int, ret_xy:bool/0/bool, ret_index:bool/0/bool · returned tuple · level recorded 2026-09-24
pcawhitenlearn_shrinkage mast3r/retrieval/model.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 68208f1e15cc2916 · report fixture: signature X:ndarray/2/float, s:float/0/float · returned tuple · level recorded 2026-09-24
reg_desc mast3r/catmlp_dpt_head.py ran licence not identified · pointer only · 2e16111f6a6717ac · report fixture: signature desc:Tensor/2/float, mode:str/0/str · returned Tensor · level recorded 2026-09-24
sel mast3r/image_pairs.py ran; the contract check could not run (RAISES) licence not identified · pointer only · a2c256044b1ba139 · report fixture: signature x:dict/0/?, kept:ndarray/1/int · returned dict · level recorded 2026-09-24
weighted_spoc mast3r/retrieval/model.py ran · our draft was wrong fingerprinted licence not identified · pointer only · f8448367aee10bcc · report fixture: signature feat:Tensor/3/float, attn:Tensor/2/float · returned Tensor · level recorded 2026-09-24
filter_pairs_seq mast3r/image_pairs.py unverified no licence file found · pointer only · d07895a2f6ed02f8 · report
load_model in 479 papers mast3r/model.py unverified licence not identified · pointer only · 9a09f31d98cc4d88 · report
matches_to_depths mast3r/cloud_opt/triangulation.py unverified licence not identified · pointer only · c030fad7954a65d2 · report

Tasks

3D Reconstruction

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