A Comprehensive Framework for 3D Occupancy Estimation in Autonomous Driving
Wanshui Gan, Ningkai Mo, Hongbin Xu, Naoto Yokoya
Abstract
3D occupancy estimation from surrounding-view images is an exciting task in autonomous driving, following the success of Bird's Eye View (BEV) perception. In this work, we present a comprehensive framework for 3D occupancy estimation, which reveals several key components for 3D occupancy estimation, such as network design, optimization, and evaluation. In addition, we explore the relationship between 3D occupancy estimation and other related tasks, such as monocular depth estimation and 3D reconstruction, which could advance the study of 3D perception in autonomous driving. For evaluation, we propose a simple sampling strategy to define the metric for occupancy evaluation, which is flexible for current public datasets. Moreover, we establish a benchmark in terms of the depth estimation metric, where we compare our proposed method with monocular depth estimation methods on the DDAD and Nuscenes datasets and achieve competitive performance. The relevant code is available in <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/GANWANSHUI/SimpleOccupancy</uri> .