DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

By Weixin Lu, Guowei Wan, Yao Zhou, Pengfei Yuan, Shiyu Song. IEEE International Conference on Computer Vision, 2019

323 citations recorded by the source corpus.

We present DeepVCP - 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 interference 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. 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 registration accuracy and runtime efficiency to the state-of-the-art geometry-based methods, but with higher robustness to inaccurate initial poses. 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 make it attractive to the substantial applications relying on the point cloud registration task.

Subfields: Aerospace Engineering, Computational Mechanics, Geology

View Paper: https://www.semanticscholar.org/paper/514d99b241c76779ca5c78eaf8eaf74ec3672684

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Rana Abbas
2. Jian Zhang
3. Yue Wang
4. Justin M. Solomon
5. Xiaoshui Huang
6. Guofeng Mei
7. Andrew Markham
8. Bo Yang

In Computational Mechanics

1. Gim Hee Lee
2. Zi Jian Yew
3. Yue Wang
4. Justin M. Solomon
5. Rana Abbas
6. Jian Zhang
7. Xiaoshui Huang
8. Guofeng Mei

In Geology

1. Rana Abbas
2. Jian Zhang
3. Yue Wang
4. Justin M. Solomon
5. Xiaoshui Huang
6. Guofeng Mei
7. Qingyong Hu
8. Bo Yang

Citations in the corpus

• A comprehensive survey on point cloud registration (2021, methodology): “Lu et al. [65] propose a method (DeepVCP) to detect keypoints based on learned matching probabilities among a group of candidates, which can boost the registration accuracy.”
• Deep Closest Point: Learning Representations for Point Cloud Registration (2019, background): “Concurrent work [26] proposes an endto-end pipeline for point cloud registration.”
• RPM-Net: Robust Point Matching Using Learned Features (2020, methodology): “Various methods can be used for this purpose, we follow [19, 35] to compute {R, t} using SVD (Section 5.”
• SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration (2020, background): “Accurate matching of partial 3D surfaces is critical for point cloud registration [17, 38, 6, 21, 29], segmentation [58, 28, 27], and recognition [24, 12, 47].”