SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.17342 · CVPR · 2023

PMatch: Paired Masked Image Modeling for Dense Geometric Matching

Xiaoming Liu, Shengjie Zhu

arXiv · PDF · Open in the Atlas

Code that ran

15 of 21 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 3 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2303.17342.json · badge: /api/ran/2303.17342.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ShngJZ/PMatch community
Papers with Code archive
15 ran · 6 no recorded run
FunctionStatusWhere it lives
CAB Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("7a16afb355653e12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DFN Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("babf93469d127ce6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GP Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("b36fd6d3ea325a2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

PositionEncodingSine Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("f5d738fa2de8f36c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

RRB Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("d4ecbc7c731291ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ToTensorScaled Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("8114c24b493bd6f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ToTensorUnscaled Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("c61ecc97ea7ee175")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TupleCompose Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("2168e2f71cd93edf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TupleNormalize Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("4e2e411dae35e79d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TupleResize Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("f72f4f70cf5da05f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TupleToTensorScaled Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("4347f118211f1976")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TupleToTensorUnscaled Ran
ran on a synthesized input
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("906f8baa705381c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

kde Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("50ff7bbc1a8ffd18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

local_correlation Ran
ran; our contract draft was wrong, not the code
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("f16dcf38e54e87f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

lower_config Ran
ran; our contract draft was wrong, not the code
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("616a327f53231192")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ConvRefiner Not yet run
unverified (harvested, no recorded run)
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("9d79df33e76c4667")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Decoder Not yet run
unverified (harvested, no recorded run)
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("ebe4ac0c04defee7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LoFTR Not yet run
unverified (harvested, no recorded run)
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("9fe2662843a9abdb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

PMatch Not yet run
unverified (harvested, no recorded run)
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("67caf3386e8cb186")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_backbone Not yet run
unverified (harvested, no recorded run)
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("bcc3bfa51d551dd7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_tuple_transform_ops Not yet run
unverified (harvested, no recorded run)
ShngJZ/PMatch/PMatch/PMatch/models/pmatch.py
pointer only (licence: NONE) · get_code("85a76414e468c146")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShngJZ/PMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 20 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
lower_config
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later
2104.00680 (2021-04)
LoFTR: Detector-Free Local Feature Matching with Transformers
2204.10144 (2022-04)
A case for using rotation invariant features in state of the art feature matchers
2209.12213 (2022-09)
ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Dense geometric matching determines the dense pixelwise correspondence between a source and support image corresponding to the same 3D structure. Prior works employ an encoder of transformer blocks to correlate the twoframe features. However, existing monocular pretraining tasks, e.g., image classification, and masked image modeling (MIM), can not pretrain the cross-frame module, yielding less optimal performance. To resolve this, we reformulate the MIM from reconstructing a single masked image to reconstructing a pair of masked images, enabling the pretraining of transformer module. Additionally, we incorporate a decoder into pretraining for improved upsampling results. Further, to be robust to the textureless area, we propose a novel cross-frame global matching module (CFGM). Since the most textureless area is planar surfaces, we propose a homography loss to further regularize its learning. Combined together, we achieve the State-of-The-Art (SoTA) performance on geometric matching. Codes and models are available at https://github.com/ShngJZ/PMatch.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.17342")
get_code_for_paper("2303.17342")
have("2303.17342")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.17342.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.17342.svg)](https://syntology.ai/paper/2303.17342)

Connect an agent — have() is free.