Point Cloud Registration

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

24 leaderboard tables shown for this task, 24 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 24 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

12 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 229 papers with code (447 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Open3D: A Modern Library for 3D Data Processing
  30 Jan 2018 14 repositories listed
  The Open3D frontend exposes a set of carefully selected data structures and algorithms in both C++ and Python.
• SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
  10 Dec 2019 13 repositories listed
  We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
• TEASER: Fast and Certifiable Point Cloud Registration
  21 Jan 2020 7 repositories listed Syntology ran 2 of 7 samples · 5 unverified · 2 pointer-only (licence)
  We propose the first fast and certifiable algorithm for the registration of two sets of 3D points in the presence of large amounts of outlier correspondences.
• PointNetLK: Robust & Efficient Point Cloud Registration using PointNet
  13 Mar 2019 7 repositories listed Syntology ran 2 of 24 samples · 22 unverified · 22 pointer-only (licence)
  To date, the successful application of PointNet to point cloud registration has remained elusive.
• PREDATOR: Registration of 3D Point Clouds with Low Overlap
  25 Nov 2020 5 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region.
• RPM-Net: Robust Point Matching using Learned Features
  30 Mar 2020 5 repositories listed Syntology ran 6 of 31 samples · 25 unverified · 14 pointer-only (licence)
  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.
• PCRNet: Point Cloud Registration Network using PointNet Encoding
  21 Aug 2019 5 repositories listed
  PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion.
• Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
  10 Mar 2021 4 repositories listed
  The code and protocols for our benchmark and algorithm are available at https://github.
• PRNet: Self-Supervised Learning for Partial-to-Partial Registration
  27 Oct 2019 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration.
• Deep Closest Point: Learning Representations for Point Cloud Registration
  8 May 2019 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  To address local optima and other difficulties in the ICP pipeline, we propose a learning-based method, titled Deep Closest Point (DCP), inspired by recent techniques in computer vision and natural language processing.
• Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
  6 Oct 2023 3 repositories listed
  This paper proposes an equivariant neural network that takes data in any semi-simple Lie algebra as input.
• PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration
  14 Jul 2024 2 repositories listed
  To further improve the distinctiveness of descriptors, we propose a position-aware convolution, which can better learn spatial information of local structures.
• NeRF-Supervised Feature Point Detection and Description
  13 Mar 2024 2 repositories listed
  Feature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition.
• Pyramid Semantic Graph-based Global Point Cloud Registration with Low Overlap
  22 Jul 2023 2 repositories listed
  In this paper, we propose a graph-theoretic framework to address the problem of global point cloud registration with low overlap.
• Density-invariant Features for Distant Point Cloud Registration
  19 Jul 2023 2 repositories listed
  Registration of distant outdoor LiDAR point clouds is crucial to extending the 3D vision of collaborative autonomous vehicles, and yet is challenging due to small overlapping area and a huge disparity between observed…
• SiLK -- Simple Learned Keypoints
  12 Apr 2023 2 repositories listed Syntology ran 4 of 6 samples · 2 unverified
  Keypoint detection & descriptors are foundational tech-nologies for computer vision tasks like image matching, 3D reconstruction and visual odometry.
• Generalized Differentiable RANSAC
  26 Dec 2022 2 repositories listed
  We propose ∇-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.
• Sliced Optimal Partial Transport
  15 Dec 2022 2 repositories listed
  Optimal transport (OT) has become exceedingly popular in machine learning, data science, and computer vision.
• Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
  29 Nov 2022 2 repositories listed
  Learning universal representations across different applications domain is an open research problem.
• Geometric Transformer for Fast and Robust Point Cloud Registration
  14 Feb 2022 2 repositories listed Syntology ran 4 of 9 samples · 5 unverified · 9 pointer-only (licence)
  Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds.
• Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
  22 Dec 2021 2 repositories listed Syntology ran 5 of 16 samples · 11 unverified
  Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
• Accurate Point Cloud Registration with Robust Optimal Transport
  1 Nov 2021 2 repositories listed
  Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric…
• FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration
  7 Jun 2021 2 repositories listed
  Data association is important in the point cloud registration.
• ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning
  28 Mar 2021 2 repositories listed
  Point cloud registration is a common step in many 3D computer vision tasks such as object pose estimation, where a 3D model is aligned to an observation.
• Robust Point Cloud Registration Framework Based on Deep Graph Matching
  7 Mar 2021 2 repositories listed Syntology ran 25 of 38 samples · 13 unverified · 38 pointer-only (licence)
  In this paper, we propose a novel deep graph matchingbased framework for point cloud registration.
• Self-supervised Geometric Perception
  4 Mar 2021 2 repositories listed
  We present self-supervised geometric perception (SGP), the first general framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels (e.
• CLIPPER: A Graph-Theoretic Framework for Robust Data Association
  20 Nov 2020 2 repositories listed
  We formulate the problem in a graph-theoretic framework using the notion of geometric consistency.
• MaskNet: A Fully-Convolutional Network to Estimate Inlier Points
  19 Oct 2020 2 repositories listed
  We demonstrate these improvements on synthetic and real-world datasets.
• Distinctive 3D local deep descriptors
  1 Sep 2020 2 repositories listed
  We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment.
• DeepGMR: Learning Latent Gaussian Mixture Models for Registration
  20 Aug 2020 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics.

Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.