PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

2019-03-13 · CVPR 2019 6 · Yasuhiro Aoki, Hunter Goforth, Rangaprasad Arun Srivatsan, Simon Lucey

PointNet has revolutionized how we think about representing point clouds. For classification and segmentation tasks, the approach and its subsequent extensions are state-of-the-art. To date, the successful application of PointNet to point cloud registration has remained elusive. In this paper we argue that PointNet itself can be thought of as a learnable "imaging" function. As a consequence, classical vision algorithms for image alignment can be applied on the problem - namely the Lucas & Kanade (LK) algorithm. Our central innovations stem from: (i) how to modify the LK algorithm to accommodate the PointNet imaging function, and (ii) unrolling PointNet and the LK algorithm into a single trainable recurrent deep neural network. We describe the architecture, and compare its performance against state-of-the-art in common registration scenarios. The architecture offers some remarkable properties including: generalization across shape categories and computational efficiency - opening up new paths of exploration for the application of deep learning to point cloud registration. Code and videos are available at https://github.com/hmgoforth/PointNetLK.

📄 PDF Abstract BibTeX arXiv:1903.05711

Code (7)

hmgoforth/PointNetLK 공식 구현 pytorch

code-implementation1/Code9/tree/main/PVNet mindspore

code-implementation1/Code9/tree/main/PointNet mindspore

izhangrui/paper_to_read

julians89/PointNetLK-Tensorflow tf

vinits5/PointNetLK pytorch

vinits5/learning3d pytorch

Tasks

Computational Efficiency Point Cloud Registration Rolling Shutter Correction

Methods 이 논문이 사용한 방법론

eToro Customer Care Number +1-833-534-1729 설명 없음

CorsNet: 3D Point Cloud Registration by Deep Neural Network

2020-02-03 · Akiyoshi Kurobe, Yusuke Sekikawa, Kohta Ishikawa, and Hideo Saito

Point cloud registration is a key problem for robotics and computer vision communities. This represents estimating a rigid transform which aligns one point cloud to another. Iterative closest point (ICP) is a well-kno…

Deep Learning Point Cloud Registration

Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)

2020-09-02 · Pranav Kadam, Min Zhang, Shan Liu, C. -C. Jay Kuo

An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work. The proposed SPA method can register two point clouds effectively using only a small subset of salient poin…

Deep Learning Point Cloud Registration Single Particle Analysis

PointNetLK Revisited

2020-08-21 · CVPR 2021 1 · Xueqian Li, Jhony Kaesemodel Pontes, Simon Lucey

We address the generalization ability of recent learning-based point cloud registration methods. Despite their success, these approaches tend to have poor performance when applied to mismatched conditions that are not we…

Point Cloud Registration

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

2019-10-27 · NeurIPS 2019 12 · Yue Wang, Justin M. Solomon

We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning-based methods for registration, we…

Point Cloud Registration Self-Supervised Learning

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation

2021-04-12 · Sk Aziz Ali, Kerem Kahraman, Gerd Reis, Didier Stricker

We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel $2^D$-tree representation for the input point sets and a hierarchical deep feature emb…