SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.05060 · 2026

R3PM-Net: Real-time, Robust, Real-world Point Matching Network

Panagiotis Meletis, Erkut Akdag, Yasaman Kashefbahrami, Evgeniya Balmashnova, Dip Goswami, Egor Bondarau

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2604.05060.json · badge: /api/ran/2604.05060.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
YasiiKB/R3PM-Net community
Papers with Code archive
8 ran · 2 no recorded run
FunctionStatusWhere it lives
ParameterPredictionNet Ran
ran on a synthesized input
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("e711607ae5d1d3a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

angle_difference Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("e9edd3a69600514a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

convert2transformation Ran
ran; our contract draft was wrong, not the code
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("5733e2250709fea3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

match_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("012b727c0a5d4b62")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

se3_transform Ran
ran; our contract draft was wrong, not the code
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("839cd5d34b4eb83b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

sinkhorn Ran
ran on a synthesized input
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("6de325d6b2842746")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

square_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("3f5fbb460e98663b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

to_numpy Ran
ran, honoured the contract we drafted
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("a2a91d3eb9618070")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

R3PMNet Not yet run
unverified (harvested, no recorded run)
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("c2e1d354090e593d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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.

compute_rigid_transform Not yet run
unverified (harvested, no recorded run)
YasiiKB/R3PM-Net/r3pm_net/model.py
pointer only (licence: NONE) · get_code("423a9cb007e946bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasiiKB/R3PM-Net 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
square_distance
brick of this paper's assembly: helper
3 other papers
3 dated earlier
2003.13479 (2020-03)
RPM-Net: Robust Point Matching using Learned Features
2103.04256 (2021-03)
Robust Point Cloud Registration Framework Based on Deep Graph Matching
2310.17359 (2023-10)
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
angle_difference
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2003.13479 (2020-03)
RPM-Net: Robust Point Matching using Learned Features
2310.17359 (2023-10)
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
compute_rigid_transform
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2003.13479 (2020-03)
RPM-Net: Robust Point Matching using Learned Features
sinkhorn
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2003.13479 (2020-03)
RPM-Net: Robust Point Matching using Learned Features
to_numpy
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2003.13479 (2020-03)
RPM-Net: Robust Point Matching using Learned Features

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

Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two point clouds. While deep-learning methods have addressed key limitations of traditional non-learning approaches, such as sensitivity to noise, outliers, occlusion, and initialization, they are developed and evaluated on clean, dense, synthetic datasets (limiting their generalizability to real-world industrial scenarios). This paper introduces R3PM-Net, a lightweight, global-aware, object-level point matching network designed to bridge this gap by prioritizing both generalizability and real-time efficiency. To support this transition, two datasets, Sioux-Cranfield and Sioux-Scans, are proposed. They provide an evaluation ground for registering imperfect photogrammetric and event-camera scans to digital CAD models, and have been made publicly available. Extensive experiments demonstrate that R3PM-Net achieves competitive accuracy with unmatched speed. On ModelNet40, it reaches a perfect fitness score of 1 and inlier RMSE of 0.029 cm in only 0.007s, approximately 7× faster than the state-of-the-art method RegTR [35]. This performance carries over to the Sioux-Cranfield dataset, maintaining a fitness of 1 and inlier RMSE of 0.030 cm with similarly low latency. Furthermore, on the highly challenging Sioux-Scans dataset, R3PM-Net successfully resolves edge cases in under 50 ms. These results confirm that R3PM-Net offers a robust, high-speed solution for critical industrial applications, where precision and real-time performance are indispensable. The code and datasets are available at https://github.com/YasiiKB/R3PM-Net.

For agents

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

get_harvested_code_for_paper("2604.05060")
get_code_for_paper("2604.05060")
have("2604.05060")

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

curl https://syntology.ai/api/ran/2604.05060.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.05060.svg)](https://syntology.ai/paper/2604.05060)

Connect an agent — have() is free.