Voxel-MAE: Masked Autoencoders for Self-supervised Pre-training Large-scale Point Clouds. (arXiv:2206.09900v5 [cs.CV] UPDATED)

Current perception models in autonomous driving greatly rely on large-scale
labeled 3D data. However, it is expensive and time-consuming to annotate 3D
data. In this work, we aim at facilitating research on self-supervised learning
from the vast unlabeled 3D data in autonomous driving. We introduce a masked
autoencoding framework for pre-training large-scale point clouds, dubbed
Voxel-MAE. We take advantage of the geometric characteristics of large-scale
point clouds, and propose the range-aware random masking strategy and binary
voxel classification task. Specifically, …

arxiv pre-training scale training voxel