SE3ET: SE(3)-Equivariant Transformer for Low-Overlap Point Cloud Registration

ACCEPTED JUL Y, 2024 1 SE3ET: SE(3)-Equivariant Transformer for Low-Overlap Point Cloud Registration Chien Erh Lin, Minghan Zhu, and Maani Ghaffari Abstract --Partial point cloud registration is a challenging problem in robotics, especially when the robot undergoes a large transformation, causing a significant initial pose error and a low overlap between measurements. This work proposes exploiting equivariant learning from 3D point clouds to improve registration robustness. We propose SE3ET, an SE(3)-equivariant registration framework that employs equivariant point convolution and equivariant transformer designs to learn expressive and robust geometric features. We tested the proposed registration method on indoor and outdoor benchmarks where the point clouds are under arbitrary transformations and low overlapping ratios. We also provide generalization tests and run-time performance. I NTRODUCTION P OINT cloud registration has gained significant attention recently due to advancements in 3D sensor technology and computational resources. It seeks to determine the optimal transformation between two point clouds, addressing core challenges in computer vision, computer graphics, and robotics [1], [2]. These tasks include 3D localization, 3D reconstruction, pose estimation, and simultaneous localization and mapping (SLAM) [3]. Partial-to-partial registration is widespread yet challenging in robotics applications. Many point cloud registration methods require sufficient overlap between two point clouds to find an accurate transformation [4].