Robust Partial-to-Partial Point Cloud Registration in a Full Range

Registration of 3D objects from point clouds is a challenging task due to sparse and noisy measurements, incomplete observations, and large transformations. In this work, we propose the
G
raph
M
atching
C
onsensus
Net
work (
GMCNet
) to estimate faithful correspondences for full-range Partial-to-Partial point cloud Registration (PPR) in object-level registration scenarios. To encode robust point descriptors, we employ a novel Transformation-robust Point Transformer (
TPT
) module to adaptively aggregate local features with respect to the structural relations, taking advantage of both handcrafted rotation-invariant (
RI
) features and noise-resilient spatial coordinates. Based on the synergy of hierarchical graph networks and graphical modeling, we propose the Hierarchical Graphical Modeling (
HGM
) architecture to encode robust descriptors comprising of i) a unary term learned from
RI
features, and ii) multiple smoothness terms encoded from neighboring point relations at different scales through our TPT modules. Extensive experiments show that GMCNet outperforms previous state-of-the-art methods for PPR.