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

TL;DR

This paper introduces EDFNet, a task-specific 3D point cloud descriptor that enhances matching robustness by exploiting local structures and multi-scale features through a specialized encoder and dynamic fusion.

Contribution

The paper proposes a novel descriptor learning method combining local geometry and repetitive structures with a dynamic fusion module for improved 3D point cloud matching.

Findings

Enhanced matching accuracy on benchmark datasets

Robustness against noise, partiality, and deformation

Outperforms existing descriptors in keypoint correspondence tasks

Abstract

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, \etc, 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. ...