DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration

by   Weixin Lu, et al.
Baidu, Inc.

We present DeepICP - a novel end-to-end learning-based 3D point cloud registration framework that achieves comparable registration accuracy to prior state-of-the-art geometric methods. Different from other keypoint based methods where a RANSAC procedure is usually needed, we implement the use of various deep neural network structures to establish an end-to-end trainable network. Our keypoint detector is trained through this end-to-end structure and enables the system to avoid the inference of dynamic objects, leverages the help of sufficiently salient features on stationary objects, and as a result, achieves high robustness. Rather than searching the corresponding points among existing points, the key contribution is that we innovatively generate them based on learned matching probabilities among a group of candidates, which can boost the registration accuracy. Our loss function incorporates both the local similarity and the global geometric constraints to ensure all above network designs can converge towards the right direction. We comprehensively validate the effectiveness of our approach using both the KITTI dataset and the Apollo-SouthBay dataset. Results demonstrate that our method achieves comparable or better performance than the state-of-the-art geometry-based methods. Detailed ablation and visualization analysis are included to further illustrate the behavior and insights of our network. The low registration error and high robustness of our method makes it attractive for substantial applications relying on the point cloud registration task.


page 4

page 8


End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

3D Point cloud registration is still a very challenging topic due to the...

Learning Dense Features for Point Cloud Registration Using Graph Attention Network

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

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

We present a simple, flexible, and general framework titled Partial Regi...

DFC: Deep Feature Consistency for Robust Point Cloud Registration

How to extract significant point cloud features and estimate the pose be...

UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor

It is hard to create consistent ground truth data for interest points in...

Elastic Registration of Geodesic Vascular Graphs

Vascular graphs can embed a number of high-level features, from morpholo...

SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention

This paper proposes a GNN-based method for exploiting semantics and loca...

Please sign up or login with your details

Forgot password? Click here to reset