Masked Autoencoders for Self-Supervised Learning on Automotive Point Clouds

Masked autoencoding has become a successful pre-training paradigm for Transformer models for text, images, and recently, point clouds. Raw automotive datasets are a suitable candidate for self-supervised pre-training as they generally are cheap to collect compared to annotations for tasks like 3D object detection (OD). However, 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 point clouds which are small, dense and have homogeneous point density. In this work, we study masked autoencoding for point clouds in an automotive setting, which are sparse and for which the point density can vary drastically among objects in the same scene. To this end, we propose Voxel-MAE, a simple masked autoencoding pre-training scheme designed for voxel representations. We pre-train the backbone of a Transformer-based 3D object detector to reconstruct masked voxels and to distinguish between empty and non-empty voxels. Our method improves the 3D OD performance by 1.75 mAP points and 1.05 NDS on the challenging nuScenes dataset. Compared to existing self-supervised methods for automotive data, Voxel-MAE displays up to $2\times$ performance increase. Further, we show that by pre-training with Voxel-MAE, we require only 40% of the annotated data to outperform a randomly initialized equivalent. Code will be released.