Open access
Sep 2026
Self-Supervised 3D Point Cloud Detection with Depthwise Separable Masked Autoencoders
DS-MAE introduces a pyramidal transformer encoder with depthwise separable attention to enhance local geometric feature extraction while reducing computational cost and a density-aware reconstruction loss accounts for the non-uniform point density of LiDAR observations.
Jia-Yi Zhou, Yaqian Ning, Jie Cao et al.
· Remote Sensing · 0 citations