Deep Global Registration

2020/04/24 by Choy, Christopher, Dong, Wei, Koltun, Vladlen · 16 citations
#Computational Geometry (cs.CG) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2004.11540

Abstract

We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspondence confidence prediction, a differentiable Weighted Procrustes algorithm for closed-form pose estimation, and a robust gradient-based SE(3) optimizer for pose refinement. Experiments demonstrate that our approach outperforms state-of-the-art methods, both learning-based and classical, on real-world data.

Cited by

• Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation
• Masked Registration and Autoencoding of CT Images for Predictive Tibia Reconstruction
• Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration
• FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)^N Diffusion Refinement
• Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
• PointCNN++: Performant Convolution on Native Points
• ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance
• Quality-controlled registration of urban MLS point clouds reducing drift effects by adaptive fragmentation
• Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
• DINOReg: Strong Point Cloud Registration with Vision Foundation Model
• Robust Point Cloud Registration via Geometric Overlapping Guided Rotation Search
• DualReg: Dual-Space Filtering and Reinforcement for Rigid Registration
• Surfel-based 3D Registration with Equivariant SE(3) Features
• Combinative Matching for Geometric Shape Assembly
• PKSS-Align: Robust Point Cloud Registration on Pre-Kendall Shape Space
• Correspondence-Free Fast and Robust Spherical Point Pattern Registration

Related

• 3D Local Features for Direct Pairwise Registration
• DeepGMR: Learning Latent Gaussian Mixture Models for Registration
• FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)^N Diffusion Refinement
• Deep Hough Voting for Robust Global Registration
• Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector