D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

by   Xuyang Bai, et al.

A successful point cloud registration often lies on robust establishment of sparse matches through discriminative 3D local features. Despite the fast evolution of learning-based 3D feature descriptors, little attention has been drawn to the learning of 3D feature detectors, even less for a joint learning of the two tasks. In this paper, we leverage a 3D fully convolutional network for 3D point clouds, and propose a novel and practical learning mechanism that densely predicts both a detection score and a description feature for each 3D point. In particular, we propose a keypoint selection strategy that overcomes the inherent density variations of 3D point clouds, and further propose a self-supervised detector loss guided by the on-the-fly feature matching results during training. Finally, our method achieves state-of-the-art results in both indoor and outdoor scenarios, evaluated on 3DMatch and KITTI datasets, and shows its strong generalization ability on the ETH dataset. Towards practical use, we show that by adopting a reliable feature detector, sampling a smaller number of features is sufficient to achieve accurate and fast point cloud alignment.[code release](https://github.com/XuyangBai/D3Feat)


page 8

page 13

page 14


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...

Learning Dense Features for Point Cloud Registration Using Graph Attention Network

Point cloud registration is a fundamental task in many applications such...

USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds

In this paper, we propose the USIP detector: an Unsupervised Stable Inte...

HD2Reg: Hierarchical Descriptors and Detectors for Point Cloud Registration

Feature Descriptors and Detectors are two main components of feature-bas...

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

In this paper, we propose the 3DFeat-Net which learns both 3D feature de...

ASLFeat: Learning Local Features of Accurate Shape and Localization

This work focuses on mitigating two limitations in the joint learning of...

3D Point Cloud Registration with Multi-Scale Architecture and Self-supervised Fine-tuning

We present MS-SVConv, a fast multi-scale deep neural network that output...

Please sign up or login with your details

Forgot password? Click here to reset