Autonomous driving, in recent years, has been receiving increasing attention for its potential
to relieve drivers' burdens and improve the safety of driving. In modern autonomous driving …

Autonomous vehicles require constant environmental perception to obtain the distribution of
obstacles to achieve safe driving. Specifically, 3D object detection is a vital functional …

Abstract 3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal
undertaking in autonomous driving aiming to predict the voxel occupancy within volumetric …

In this paper, we propose a long-sequence modeling framework, named StreamPETR, for
multi-view 3D object detection. Built upon the sparse query design in the PETR series, we …

Abstract 3D scene understanding plays a vital role in vision-based autonomous driving.
While most existing methods focus on 3D object detection, they have difficulty describing …

Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This
appealing ability is vital for recognition and understanding. To enable such capability in AI …

Robotic perception requires the modeling of both 3D geometry and semantics. Existing
methods typically focus on estimating 3D bounding boxes, neglecting finer geometric details …

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a
model for a single task with supervision. We propose OpenScene, an alternative approach …

We present a novel bird's-eye-view (BEV) detector with perspective supervision, which
converges faster and better suits modern image backbones. Existing state-of-the-art BEV …

Autonomous driving requires a comprehensive understanding of the surrounding
environment for reliable trajectory planning. Previous works rely on dense rasterized scene …