Overlap-guided Gaussian Mixture Models for Point Cloud Registration
This addresses the problem of robust point cloud registration for applications like robotics and computer vision, though it is incremental as it builds on existing probabilistic approaches.
The paper tackles the challenge of registering 3D point clouds with partial overlap by proposing an overlap-guided probabilistic method that aligns Gaussian Mixture Models, achieving superior accuracy and efficiency compared to state-of-the-art methods on synthetic and real-world datasets.
Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations. However, registering point cloud pairs in the case of partial overlap is still a challenge. This paper proposes a novel overlap-guided probabilistic registration approach that computes the optimal transformation from matched Gaussian Mixture Model (GMM) parameters. We reformulate the registration problem as the problem of aligning two Gaussian mixtures such that a statistical discrepancy measure between the two corresponding mixtures is minimized. We introduce a Transformer-based detection module to detect overlapping regions, and represent the input point clouds using GMMs by guiding their alignment through overlap scores computed by this detection module. Experiments show that our method achieves superior registration accuracy and efficiency than state-of-the-art methods when handling point clouds with partial overlap and different densities on synthetic and real-world datasets. https://github.com/gfmei/ogmm