DeepGMR: Learning Latent Gaussian Mixture Models for Registration
This addresses a fundamental problem in 3D computer vision, graphics, and robotics, offering a novel probabilistic learning-based solution for registration tasks.
The paper tackles point cloud registration under large transformations, noise, and time constraints by introducing DeepGMR, a learning-based method that formulates registration as minimizing KL-divergence between Gaussian mixture models, resulting in a real-time, robust approach that shows favorable performance compared to state-of-the-art methods.
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.