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

Abstract

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.

10 pages, 6 figures, 3 tables, typos corrected, experimental results updated, accepted by ICCV 2019

References in corpus (5)

• Point-Set Registration: Coherent Point Drift
• Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• Robust and Precise Vehicle Localization based on Multi-sensor Fusion in Diverse City Scenes
• SegICP: Integrated Deep Semantic Segmentation and Pose Estimation

Cited by in corpus (15)

• RPM-Net: Robust Point Matching using Learned Features
• Vision-based Robotic Grasping From Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Review
• Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment
• A review of laser scanning for geological and geotechnical applications in underground mining
• BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM
• A Rotation-Invariant Framework for Deep Point Cloud Analysis
• KSS-ICP: Point Cloud Registration based on Kendall Shape Space
• VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registration
• PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
• DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registration
• LPRnet: A self-supervised registration network for LiDAR and photogrammetric point clouds
• Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations
• Automatic clustering of Celtic coins based on 3D point cloud pattern analysis
• Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
• NeuralBoneReg: An Instance-Specific Label-Free Point Cloud-Based Method for Multi-Modal Bone Surface Registration