PCRNet: Point Cloud Registration Network using PointNet Encoding

Abstract

PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion. However, recent works in literature have shown the sensitivity of the PointNet representation to pose misalignment. This paper presents a novel framework that uses the PointNet representation to align point clouds and perform registration for applications such as tracking, 3D reconstruction and pose estimation. We develop a framework that compares PointNet features of template and source point clouds to find the transformation that aligns them accurately. Depending on the prior information about the shape of the object formed by the point clouds, our framework can produce approaches that are shape specific or general to unseen shapes. The shape specific approach uses a Siamese architecture with fully connected (FC) layers and is robust to noise and initial misalignment in data. We perform extensive simulation and real-world experiments to validate the efficacy of our approach and compare the performance with state-of-art approaches.

References in corpus (6)

• Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
• 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
• Dynamic Graph CNN for Learning on Point Clouds
• Iterative Transformer Network for 3D Point Cloud
• Fast and Accurate Point Cloud Registration using Trees of Gaussian Mixtures
• PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

Cited by in corpus (15)

• RPM-Net: Robust Point Matching using Learned Features
• A Benchmark for Point Clouds Registration Algorithms
• Point Cloud Registration using Representative Overlapping Points
• Multi-Features Guidance Network for partial-to-partial point cloud registration
• Robust Point Cloud Registration Framework Based on Deep Graph Matching
• Robust Partial-to-Partial Point Cloud Registration in a Full Range
• Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations
• MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling
• Correspondence Matrices are Underrated
• DMLO: Deep Matching LiDAR Odometry
• Tabulated MLP for Fast Point Feature Embedding
• GenReg: Deep Generative Method for Fast Point Cloud Registration
• A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras
• Irregularly Tabulated MLP for Fast Point Feature Embedding
• Shape registration in the time of transformers