Papers › RPM-Net: Robust Point Matching using Learned Features

RPM-Net: Robust Point Matching using Learned Features

30 Mar 2020CVPR 2020 6arXiv:2003.13479archive 2025-07-28

Zi Jian Yew, Gim Hee Lee

Iterative Closest Point (ICP) solves the rigid point cloud registration problem iteratively in two steps: (1) make hard assignments of spatially closest point correspondences, and then (2) find the least-squares rigid transformation. The hard assignments of closest point correspondences based on spatial distances are sensitive to the initial rigid transformation and noisy/outlier points, which often cause ICP to converge to wrong local minima. In this paper, we propose the RPM-Net -- a less sensitive to initialization and more robust deep learning-based approach for rigid point cloud registration. To this end, our network uses the differentiable Sinkhorn layer and annealing to get soft assignments of point correspondences from hybrid features learned from both spatial coordinates and local geometry. To further improve registration performance, we introduce a secondary network to predict optimal annealing parameters. Unlike some existing methods, our RPM-Net handles missing correspondences and point clouds with partial visibility. Experimental results show that our RPM-Net achieves state-of-the-art performance compared to existing non-deep learning and recent deep learning methods. Our source code is available at the project website https://github.com/yewzijian/RPMNet .

PaperPDFConference PDFCodeCode 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 31 code samples harvested from 2 repositories linked to this paper: 26 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 0 violated, 24 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 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, 15 ran (14 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 14 samples from 1 repository, 11 ran (11 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yewzijian/RPMNet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 15 ran (1 instrument-failed) · 2 unverified report
qinzheng93/geotransformer mentioned on GitHubpytorchMITSyntology: not harvested report
vinits5/learning3d mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified), Dynamic Graph CNN for Learning on Point Clouds (arXiv:1801.07829; that paper's own run record: 16 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 28 unverified), PointConv: Deep Convolutional Networks on 3D Point Clouds (arXiv:1811.07246; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
vinits5/masknet mentioned on GitHubpytorchMITSyntology: 14 samples, 11 ran (0 instrument-failed) · 3 unverified report
zhileichen99/utopic mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robust Point Cloud Registration Framework Based on Deep Graph Matching (arXiv:2103.04256; that paper's own run record: 26 ran (of which 6 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

31 samples harvested: 26 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 0 violated, 24 with no contract checked; 1 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.

1ran · honoured contract
1ran; the contract check could not run
24ran
5unverified

Licence: 16 of the 31 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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.

yewzijian/RPMNet official repository 17 samples, 15 ran (1 instrument-failed) · 2 unverified
angle_difference src/models/pointnet_util.py ran fingerprinted MIT (permissive) · e6531f546e55f6af · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float · returned Tensor · level recorded 2026-09-24
concatenate in 8 papers src/common/math/se3.py ran fingerprinted MIT (permissive) · 8a632dcefddc5fc1 · report fixture: signature a:ndarray/2/float, b:ndarray/2/float · returned ndarray · level recorded 2026-09-25
concatenate in 8 papers src/common/math_torch/se3.py ran fingerprinted MIT (permissive) · 5eef8614474cef47 · report fixture: signature a:Tensor/3/float, b:Tensor/3/float · returned Tensor · level recorded 2026-09-25
get_postpool src/models/feature_nets.py ran MIT (permissive) · 552ad03917659f63 · report fixture: signature in_dim:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-24
get_prepool src/models/feature_nets.py ran MIT (permissive) · 8778312931854a3b · report fixture: signature in_dim:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-24
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/common/math_torch/se3.py ran MIT (permissive) · 89304006422410bd · report fixture: signature batch_size:int/0/int · returned Tensor · level recorded 2026-09-25
index_points in 49 papers src/models/pointnet_util.py ran MIT (permissive) · 0188255c8db5f0c5 · report fixture: signature points:Tensor/3/float, idx:Tensor/2/int · returned Tensor · level recorded 2026-09-24
inverse in 15 papers src/common/math/se3.py ran fingerprinted MIT (permissive) · caea4df4266011b9 · report fixture: signature g:ndarray/2/float · returned ndarray · level recorded 2026-09-25
inverse in 15 papers src/common/math_torch/se3.py ran fingerprinted MIT (permissive) · c3f07450b8d24c41 · report fixture: signature g:Tensor/3/float · returned Tensor · level recorded 2026-09-25
sinkhorn in 47 papers
census: 11 implementations from 11 papers, 11 distinct outputs across 2 buckets, one shared input per bucket
src/models/rpmnet.py ran MIT (permissive) · d9502fe2fe76bf06 · report fixture: signature log_alpha:Tensor/3/float, n_iters:int/0/int, slack:bool/0/bool, eps:int/0/int · returned Tensor · level recorded 2026-09-25
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
src/models/pointnet_util.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 4db73dd57b5d6162 · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float · returned Tensor · level recorded 2026-09-22
to_numpy in 103 papers
census: 24 implementations from 29 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
src/common/torch.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · a2a91d3eb9618070 · report fixture: signature tensor:Tensor/2/float · returned ndarray · level recorded 2026-09-22
transform in 65 papers
census: 6 implementations from 7 papers, 6 distinct outputs across 5 buckets, one shared input per bucket
src/common/math/se3.py ran fingerprinted MIT (permissive) · 9658f194c41b4f13 · report fixture: signature g:ndarray/2/float, pts:ndarray/2/float · returned ndarray · level recorded 2026-09-25
transform in 65 papers
census: 6 implementations from 7 papers, 6 distinct outputs across 5 buckets, one shared input per bucket
src/common/math/so3.py ran fingerprinted MIT (permissive) · 01535a12b106422c · report fixture: signature g:ndarray/2/float, pts:ndarray/2/float · returned ndarray · level recorded 2026-09-25
uniform_2_sphere src/common/math/random.py ran fingerprinted MIT (permissive) · a020832e85dfd32f · report fixture: signature num:int/0/int · returned ndarray · level recorded 2026-09-25
compute_rigid_transform src/models/rpmnet.py unverified MIT (permissive) · d79505bf2d1d5cb9 · report
dcm2euler src/common/math/so3.py unverified MIT (permissive) · 7944c9b1c74881cb · report
vinits5/masknet community (archive-listed) 14 samples, 11 ran (0 instrument-failed) · 3 unverified
add_outliers evaluation/create_statistical_data.py ran MIT recorded; this copy not marked cleared · pointer only · 5706ca4fef0f2696 · report fixture: signature pointcloud:Tensor/2/float, gt_mask:Tensor/1/float, size:int/0/int · returned tuple · level recorded 2026-09-24
classification_loss in 9 papers learning3d/losses/classification.py ran MIT recorded; this copy not marked cleared · pointer only · 78cd571bf9c38cc0 · report fixture: signature prediction:Tensor/2/float, target:Tensor/1/int · returned Tensor · level recorded 2026-09-24
farthest_subsample_points evaluation/create_statistical_data.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 1f8e2a3d2a65c39a · report fixture: signature pointcloud1:ndarray/2/float, num_subsampled_points:int/0/int · returned tuple · level recorded 2026-09-24
find_pretrained_path registration.py ran MIT recorded; this copy not marked cleared · pointer only · b0f6aff69d22bcdd · report fixture: returned str · level recorded 2026-09-24
flip_geometries 3dmatch/plot_figures.py ran MIT recorded; this copy not marked cleared · pointer only · f41a4accdacef815 · report fixture: signature pcds:list/1/MockPointCloud · returned list · level recorded 2026-09-24
get_angle_data evaluation/plot_results.py ran MIT recorded; this copy not marked cleared · pointer only · 39959096693129c5 · report fixture: signature results:dict/0/?, metric_key:str/0/str · returned list · level recorded 2026-09-24
get_files in 30 papers 3dmatch/make_video.py ran MIT recorded; this copy not marked cleared · pointer only · a45813b942a85200 · report fixture: signature root_dir:str/0/str · returned tuple · level recorded 2026-09-24
get_noise_data evaluation/plot_results.py ran MIT recorded; this copy not marked cleared · pointer only · fbc79bc476871f2f · report fixture: signature results:dict/0/?, metric_key:str/0/str · returned list · level recorded 2026-09-24
pc2points evaluation/evaluate_stats.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 9e2e626d60f3368d · report fixture: signature data:Tensor/3/float · returned Tensor · level recorded 2026-09-24
read_all_files evaluation/plot_results.py ran MIT recorded; this copy not marked cleared · pointer only · 35d8b1f2dc9d527e · report fixture: signature files:list/1/str · returned list · level recorded 2026-09-24
read_data in 132 papers 3dmatch/plot_figures.py ran MIT recorded; this copy not marked cleared · pointer only · a326f2a06da4eba0 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
chamfer_distance in 17 papers learning3d/losses/chamfer_distance.py unverified MIT recorded; this copy not marked cleared · pointer only · 1adcfbd14aa61be6 · report
emd learning3d/losses/emd.py unverified MIT recorded; this copy not marked cleared · pointer only · b83c09e9a41febed · report
selectROI 3dmatch/make_video.py unverified MIT recorded; this copy not marked cleared · pointer only · 5ae801ea174c3f2d · report

Tasks

Deep LearningPoint Cloud Registration

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: RPM-Net

RPM-Net

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