Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds

by   Zhiyuan Zhang, et al.

Existing learning-based point feature descriptors are usually task-agnostic, which pursue describing the individual 3D point clouds as accurate as possible. However, the matching task aims at describing the corresponding points consistently across different 3D point clouds. Therefore these too accurate features may play a counterproductive role due to the inconsistent point feature representations of correspondences caused by the unpredictable noise, partiality, deformation, , in the local geometry. In this paper, we propose to learn a robust task-specific feature descriptor to consistently describe the correct point correspondence under interference. Born with an Encoder and a Dynamic Fusion module, our method EDFNet develops from two aspects. First, we augment the matchability of correspondences by utilizing their repetitive local structure. To this end, a special encoder is designed to exploit two input point clouds jointly for each point descriptor. It not only captures the local geometry of each point in the current point cloud by convolution, but also exploits the repetitive structure from paired point cloud by Transformer. Second, we propose a dynamical fusion module to jointly use different scale features. There is an inevitable struggle between robustness and discriminativeness of the single scale feature. Specifically, the small scale feature is robust since little interference exists in this small receptive field. But it is not sufficiently discriminative as there are many repetitive local structures within a point cloud. Thus the resultant descriptors will lead to many incorrect matches. In contrast, the large scale feature is more discriminative by integrating more neighborhood information. ...


page 1

page 4

page 7

page 10


A comprehensive review of 3D point cloud descriptors

The introduction of inexpensive 3D data acquisition devices has promisin...

Direct Image to Point Cloud Descriptors Matching for 6-DOF Camera Localization in Dense 3D Point Cloud

We propose a novel concept to directly match feature descriptors extract...

PPFNet: Global Context Aware Local Features for Robust 3D Point Matching

We present PPFNet - Point Pair Feature NETwork for deeply learning a glo...

Edge-Selective Feature Weaving for Point Cloud Matching

This paper tackles the problem of accurately matching the points of two ...

Geometric robust descriptor for 3D point cloud

We propose rotation robust and density robust local geometric descriptor...

Learning Compact Geometric Features

We present an approach to learning features that represent the local geo...

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

Accurately describing and detecting 2D and 3D keypoints is crucial to es...

Please sign up or login with your details

Forgot password? Click here to reset