Zusammenfassung
In recent years, point clouds have earned quite some research interests by
the development of depth sensors. Due to different layouts of objects,
orientation of point clouds is often unknown in real applications. In this
paper, we propose a new point sets learning framework named Pointwise
Rotation-Invariant Network (PRIN), focusing on the rotation problem in point
clouds. We construct spherical signals by adaptive sampling from sparse points
and employ spherical convolutions, together with tri-linear interpolation to
extract rotation-invariant features for each point. Our network can be applied
in applications ranging from object classification, part segmentation, to 3D
feature matching and label alignment. PRIN shows similar performance on par or
better than state-of-the-art methods on part segmentation without data
augmentation. We provide theoretical analysis for what our network has learned
and why it is robust to input rotation. Our code is available online.
Nutzer