PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

Code

• github.com/hmgoforth/PointNetLK
  OfficialIn paperpytorch★ 0
• github.com/vinits5/learning3d
  pytorch★ 853
• github.com/julians89/PointNetLK-Tensorflow
  tf★ 0
• github.com/izhangrui/paper_to_read
  none★ 0
• github.com/code-implementation1/Code9/tree/main/PVNet
  mindspore★ 0
• github.com/vinits5/PointNetLK
  pytorch★ 0
• github.com/code-implementation1/Code9/tree/main/PointNet
  mindspore★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions