DeepGMR: Learning Latent Gaussian Mixture Models for Registration
arXiv:2008.09088
Abstract
Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics. For the last few decades, existing registration algorithms have struggled in situations with large transformations, noise, and time constraints. In this paper, we introduce Deep Gaussian Mixture Registration (DeepGMR), the first learning-based registration method that explicitly leverages a probabilistic registration paradigm by formulating registration as the minimization of KL-divergence between two probability distributions modeled as mixtures of Gaussians. We design a neural network that extracts pose-invariant correspondences between raw point clouds and Gaussian Mixture Model (GMM) parameters and two differentiable compute blocks that recover the optimal transformation from matched GMM parameters. This construction allows the network learn an SE(3)-invariant feature space, producing a global registration method that is real-time, generalizable, and robust to noise. Across synthetic and real-world data, our proposed method shows favorable performance when compared with state-of-the-art geometry-based and learning-based registration methods.
ECCV 2020 spotlight
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Point-Set Registration: Coherent Point Drift
- Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
- Rigid and Articulated Point Registration with Expectation Conditional Maximization
- Blind MultiChannel Identification and Equalization for Dereverberation and Noise Reduction based on Convolutive Transfer Function
- Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization
- PRNet: Self-Supervised Learning for Partial-to-Partial Registration
- TEASER: Fast and Certifiable Point Cloud Registration