English
Related papers

Related papers: RPM-Net: Robust Point Matching using Learned Featu…

200 papers

3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Lifa Zhu , Dongrui Liu , Changwei Lin , Rui Yan , Francisco Gómez-Fernández , Ninghua Yang , Ziyong Feng

Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented reality, and scene understanding. However, the performance…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Dongxu Zhang , Yingsen Wang , Yiding Sun , Haoran Xu , Peilin Fan , Jihua Zhu

The Iterative Closest Point (ICP) algorithm is one of the most important algorithms for geometric alignment of three-dimensional surface registration, which is frequently used in computer vision tasks, including the Simultaneous…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Hao Bai

In this paper, we propose a novel learning-based pipeline for partially overlapping 3D point cloud registration. The proposed model includes an iterative distance-aware similarity matrix convolution module to incorporate information from…

Computer Vision and Pattern Recognition · Computer Science 2020-08-07 Jiahao Li , Changhao Zhang , Ziyao Xu , Hangning Zhou , Chi Zhang

We describe a variation of the iterative closest point (ICP) algorithm for aligning two point sets under a set of transformations. Our algorithm is superior to previous algorithms because (1) in determining the optimal alignment, it…

Graphics · Computer Science 2009-09-29 Jeff M. Phillips , Ran Liu , Carlo Tomasi

Traditional algorithms of point set registration minimizing point-to-plane distances often achieve a better estimation of rigid transformation than those minimizing point-to-point distances. Nevertheless, recent deep-learning-based methods…

Computer Vision and Pattern Recognition · Computer Science 2022-07-15 Tatsuya Yatagawa , Yutaka Ohtake , Hiromasa Suzuki

Point cloud registration for 3D objects is a challenging task due to sparse and noisy measurements, incomplete observations and large transformations. In this work, we propose \textbf{G}raph \textbf{M}atching \textbf{C}onsensus…

Computer Vision and Pattern Recognition · Computer Science 2022-04-11 Liang Pan , Zhongang Cai , Ziwei Liu

Low-overlap regions between paired point clouds make the captured features very low-confidence, leading cutting edge models to point cloud registration with poor quality. Beyond the traditional wisdom, we raise an intriguing question: Is it…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Honghua Chen , Zeyong Wei , Yabin Xu , Mingqiang Wei , Jun Wang

We present a simple way to learn a transformation that maps samples of one distribution to the samples of another distribution. Our algorithm comprises an iteration of 1) drawing samples from some simple distribution and transforming them…

Machine Learning · Computer Science 2018-07-03 Joose Rajamäki , Perttu Hämäläinen

In this paper, we propose PCPNet, a deep-learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid-level attributes, e.g., for shape…

Computational Geometry · Computer Science 2018-06-20 Paul Guerrero , Yanir Kleiman , Maks Ovsjanikov , Niloy J. Mitra

Robust and discriminative feature learning is critical for high-quality point cloud registration. However, existing deep learning-based methods typically rely on Euclidean neighborhood-based strategies for feature extraction, which struggle…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Shuyuan Lin , Wenwu Peng , Junjie Huang , Qiang Qi , Miaohui Wang , Jian Weng

Probabilistic point cloud registration methods are becoming more popular because of their robustness. However, unlike point-to-plane variants of iterative closest point (ICP) which incorporate local surface geometric information such as…

Computer Vision and Pattern Recognition · Computer Science 2021-08-16 Weixiao Liu , Hongtao Wu , Gregory Chirikjian

This work focuses on Registration or Alignment of 3D point sets. Although the Registration problem is a well established problem and it's solved using multiple variants of Iterative Closest Point (ICP) Algorithm, most of the approaches in…

Computer Vision and Pattern Recognition · Computer Science 2021-07-22 Ashutosh Singandhupe , Hung La , Trung Dung Ngo , Van Ho

We study the problem of extracting correspondences between a pair of point clouds for registration. For correspondence retrieval, existing works benefit from matching sparse keypoints detected from dense points but usually struggle to…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 Hao Yu , Fu Li , Mahdi Saleh , Benjamin Busam , Slobodan Ilic

This paper presents DeepI2P: a novel approach for cross-modality registration between an image and a point cloud. Given an image (e.g. from a rgb-camera) and a general point cloud (e.g. from a 3D Lidar scanner) captured at different…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Jiaxin Li , Gim Hee Lee

Mapping algorithms that rely on registering point clouds inevitably suffer from local drift, both in localization and in the built map. Applications that require accurate maps, such as environmental monitoring, benefit from additional…

Robotics · Computer Science 2020-10-22 Maxime Vaidis , Johann Laconte , Vladimír Kubelka , François Pomerleau

Covariance estimation for the Iterative Closest Point (ICP) point cloud registration algorithm is essential for state estimation and sensor fusion purposes. We argue that a major source of error for ICP is in the input data itself, from the…

Robotics · Computer Science 2022-12-05 Andrea De Maio , Simon Lacroix

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. However, recent works in literature…

Computer Vision and Pattern Recognition · Computer Science 2019-12-13 Vinit Sarode , Xueqian Li , Hunter Goforth , Yasuhiro Aoki , Animesh Dhagat , Rangaprasad Arun Srivatsan , Simon Lucey , Howie Choset

Point cloud registration methods can effectively handle large-scale, partially overlapping point cloud pairs. Despite its practicality, matching the unbalanced pairs in terms of spatial extent and density has been overlooked and rarely…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Kanghee Lee , Junha Lee , Jaesik Park

Due to the density inconsistency and distribution difference between cross-source point clouds, previous methods fail in cross-source point cloud registration. We propose a density-robust feature extraction and matching scheme to achieve…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Guiyu Zhao , Zhentao Guo , Zewen Du , Hongbin Ma