Papers › Geometric Transformer for Fast and Robust Point Cloud Registration

Geometric Transformer for Fast and Robust Point Cloud Registration

14 Feb 2022CVPR 2022 1arXiv:2202.06688archive 2025-07-28

Zheng Qin, Hao Yu, Changjian Wang, Yulan Guo, Yuxing Peng, Kai Xu

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult in low-overlap scenarios, showing great potential in registration. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it robust in low-overlap cases and invariant to rigid transformation. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to $100$ times acceleration. Our method improves the inlier ratio by 17∼30 percentage points and the registration recall by over $7$ points on the challenging 3DLoMatch benchmark. Our code and models are available at \url{https://github.com/qinzheng93/GeoTransformer}.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2202.06688")

Code

Syntology Ran 4 of 9 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: community (archive-listed): 9 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

qinzheng93/geotransformer officialmentioned in papermentioned on GitHubpytorchMIT report
weitong8591/differentiable_ransac mentioned on GitHubpytorch 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

9 samples harvested; 4 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran
5unverified

Licence: 9 of the 9 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 weitong8591/differentiable_ransac. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

DGCNN_Block weitong8591/differentiable_ransac/model_cl.py community (archive-listed) ran GPL-3.0 (copyleft) · pointer only · cec0d595b6adca22 · report
DS_Block weitong8591/differentiable_ransac/model_cl.py community (archive-listed) ran GPL-3.0 (copyleft) · pointer only · b7c27509e86c1ec1 · report
GCN_Block weitong8591/differentiable_ransac/model_cl.py community (archive-listed) ran GPL-3.0 (copyleft) · pointer only · bfd2fd66fe08f211 · report
ResNet_Block weitong8591/differentiable_ransac/model_cl.py community (archive-listed) ran GPL-3.0 (copyleft) · pointer only · 3c0c44678faa330b · report
DeepRansac_CLNet weitong8591/differentiable_ransac/model_cl.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 1604305eda9b7958 · report
RANSAC weitong8591/differentiable_ransac/model_cl.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 15cf11dc4470eba4 · report
RANSACLayer weitong8591/differentiable_ransac/model_cl.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 6de1617f527431b1 · report
get_graph_feature weitong8591/differentiable_ransac/model_cl.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 8caef130745ac47b · report
knn weitong8591/differentiable_ransac/model_cl.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 115657f6be768b6b · report

Tasks

Metric LearningPoint Cloud Registration

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Cloud Registration 3DLoMatch (10-30% overlap) GeoTransformer - P2PNet Recall ( correspondence RMSE below 0.2) 74 #2 of 13 Archive leaderboard report
Point Cloud Registration 3DMatch (at least 30% overlapped - FCGF setting) GeoTransformer Recall (0.3m, 15 degrees) 95 #2 of 14 Archive leaderboard report
Point Cloud Registration FPv1 GeoTransformer RRE (degrees) 2.423 #2 of 8 Archive leaderboard report
Point Cloud Registration FPv1 GeoTransformer RTE (cm) 1.581 #2 of 8 Archive leaderboard report
Point Cloud Registration FPv1 GeoTransformer Recall (3cm, 10 degrees) 56.15 #2 of 8 Archive leaderboard report
Point Cloud Registration KITTI (FCGF setting) GeoTransformer Recall (0.6m, 5 degrees) 99.5 #1 of 11 Archive leaderboard report
Point Cloud Registration ScanNet++ (trained on 3DMatch) GeoTransformer Recall ( correspondence RMSE below 0.2) 73.4 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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