-
RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Regis...
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a... -
3DMatch and 3DLoMatch datasets
The 3DMatch and 3DLoMatch datasets are used for point cloud registration. The 3DMatch dataset contains 46 scenes for training, 8 for validation, and 8 for testing. The 3DLoMatch... -
PVT dataset
The PVT dataset is a public dataset for point cloud registration, containing 1,010 pairs of inhale and exhale lung vessel point clouds.