PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency

Abstract

Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning methods in this field, spatial consistency, which is essentially established by a Euclidean transformation between point clouds, has received almost no individual attention in existing learning frameworks. In this paper, we present PointDSC, a novel deep neural network that explicitly incorporates spatial consistency for pruning outlier correspondences. First, we propose a nonlocal feature aggregation module, weighted by both feature and spatial coherence, for feature embedding of the input correspondences. Second, we formulate a differentiable spectral matching module, supervised by pairwise spatial compatibility, to estimate the inlier confidence of each correspondence from the embedded features. With modest computation cost, our method outperforms the state-of-the-art hand-crafted and learning-based outlier rejection approaches on several real-world datasets by a significant margin. We also show its wide applicability by combining PointDSC with different 3D local descriptors.

Accepted to CVPR 2021, supplementary materials included

References in corpus (10)

• Point-Set Registration: Coherent Point Drift
• RPM-Net: Robust Point Matching using Learned Features
• 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
• Guaranteed Outlier Removal for Point Cloud Registration with Correspondences
• GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
• PRNet: Self-Supervised Learning for Partial-to-Partial Registration
• In search of inliers: 3d correspondence by local and global voting
• SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
• AdaLAM: Revisiting Handcrafted Outlier Detection
• ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants

Cited by in corpus (2)

• You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
• PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations