Point2Point: A Framework for Efficient Deep Learning on Hilbert Sorted Point Clouds with Applications in Spatio-Temporal Occupancy Prediction
Athrva Atul Pandhare,Athrva Atul Pandhare
The irregularity and permutation invariance of point cloud data pose challenges for effective learning. Conventional methods for addressing this issue involve converting raw point clouds to intermediate representations such as 3D voxel grids or range images. While such intermediate representations solve the problem of permutation invariance, they can result in significant loss of information. Appr...
