Registration is a transformation estimation problem between two point clouds, which has a
unique and critical role in numerous computer vision applications. The developments of …

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of
deep learning (DL). However, the latter faces various issues, including the lack of data or …

We study the problem of extracting accurate correspondences for point cloud registration.
Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult …

Despite recent success in incorporating learning into point cloud registration, many works
focus on learning feature descriptors and continue to rely on nearest-neighbor feature …

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

We study the problem of extracting accurate correspondences for point cloud registration.
Recent keypoint-free methods have shown great potential through bypassing the detection …

We study the problem of extracting correspondences between a pair of point clouds for
registration. For correspondence retrieval, existing works benefit from matching sparse …

Deep point cloud registration methods face challenges to partial overlaps and rely on
labeled data. To address these issues, we propose UDPReg, an unsupervised deep …

We present RoReg, a novel point cloud registration framework that fully exploits oriented
descriptors and estimated local rotations in the whole registration pipeline. Previous …

Extracting robust and general 3D local features is key to downstream tasks such as point
cloud registration and reconstruction. Existing learning-based local descriptors are either …