Soon Kwon

Re-MAE: Rethinking Masked Autoencoders towards Geometry-Aware Self-Supervised LiDAR-Based 3D Object Detection

Self-supervised pre-training with masked autoencoders has shown promise for 3D perception, yet most approaches treat LiDAR point clouds in a geometry-agnostic manner. In this paper, we introduce Re-MAE, a geometry-aware self-supervised learning framework for LiDAR-based 3D object detection that expl…