Deep Closest Point: Learning Representations for Point Cloud Registration

ICCV 2019  ·  Yue Wang, Justin M. Solomon ·

Point cloud registration is a key problem for computer vision applied to robotics, medical imaging, and other applications. This problem involves finding a rigid transformation from one point cloud into another so that they align. Iterative Closest Point (ICP) and its variants provide simple and easily-implemented iterative methods for this task, but these algorithms can converge to spurious local optima. 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. Our model consists of three parts: a point cloud embedding network, an attention-based module combined with a pointer generation layer, to approximate combinatorial matching, and a differentiable singular value decomposition (SVD) layer to extract the final rigid transformation. We train our model end-to-end on the ModelNet40 dataset and show in several settings that it performs better than ICP, its variants (e.g., Go-ICP, FGR), and the recently-proposed learning-based method PointNetLK. Beyond providing a state-of-the-art registration technique, we evaluate the suitability of our learned features transferred to unseen objects. We also provide preliminary analysis of our learned model to help understand whether domain-specific and/or global features facilitate rigid registration.

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Point Cloud Registration 3DMatch (at least 30% overlapped - FCGF setting) DCP Recall (0.3m, 15 degrees) 3.22 # 12
Visual Localization Oxford Radar RobotCar (Full-6) DCP Mean Translation Error 18.45 # 9

Methods


No methods listed for this paper. Add relevant methods here