Modern methods for vision-centric autonomous driving perception widely adopt the bird's-
eye-view (BEV) representation to describe a 3D scene. Despite its better efficiency than …

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

LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point-
or voxel-based methods as they often yield better performance than the traditional range …

The robustness of 3D perception systems under natural corruptions from environments and
sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

This paper is not motivated to seek innovation within the attention mechanism. Instead it
focuses on overcoming the existing trade-offs between accuracy and efficiency within the …

Semantic occupancy perception is essential for autonomous driving, as automated vehicles
require a fine-grained perception of the 3D urban structures. However, existing relevant …

The vision-based perception for autonomous driving has undergone a transformation from
the bird-eye-view (BEV) representations to the 3D semantic occupancy. Compared with the …

Human driver can easily describe the complex traffic scene by visual system. Such an ability
of precise perception is essential for driver's planning. To achieve this, a geometry-aware …

Densely annotating LiDAR point clouds is costly, which often restrains the scalability of fully-
supervised learning methods. In this work, we study the underexplored semi-supervised …