Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds. (arXiv:2207.00531v2 [cs.CV] UPDATED)

Masked autoencoding has become a successful pretraining paradigm for
Transformer models for text, images, and, recently, point clouds. Raw
automotive datasets are suitable candidates for self-supervised pre-training as
they generally are cheap to collect compared to annotations for tasks like 3D
object detection (OD). However, the development of masked autoencoders for
point clouds has focused solely on synthetic and indoor data. Consequently,
existing methods have tailored their representations and models toward small
and dense point clouds with homogeneous point densities.In …

arxiv autoencoder lidar masked autoencoder pre-training training