An ideal point cloud registration framework should have superior accuracy, acceptable
efficiency, and strong generalizability. However, this is highly challenging since existing …

Point cloud registration (PCR) involves determining a rigid transformation that aligns one
point cloud to another. Despite the plethora of outstanding deep learning (DL)-based …

Point cloud registration is an important task for other point cloud tasks. Feature-based
methods are widely adopted for their speed and efficiency in point cloud registration. The …

Point cloud registration is essential for many applications. However, existing real datasets
require extremely tedious and costly annotations, yet may not provide accurate camera …

Point cloud registration is the process of aligning and merging multiple point clouds into a
same coordinate system. It has many applications in computer vision, robotics, 3D …

In this paper, we present a new method for the multiview registration of point cloud. Previous
multiview registration methods rely on exhaustive pairwise registration to construct a …

This paper presents a 3D registration method with maximal cliques (MAC) for 3D point cloud
registration (PCR). The key insight is to loosen the previous maximum clique constraint and …

For point cloud registration (PCR), a matching matrix is critical. Unfortunately, the existing
approaches do not explicitly devise schemes to refine the matching matrix. Furthermore …

Despite the recent success of Transformers in point cloud registration, the cross-attention
mechanism, while enabling point-wise feature exchange between point clouds, suffers from …

Real point cloud registration, involving homologous and cross-source 3D data, poses
significant challenges such as partial overlap, high noise, density disparities, and scale …