Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending
and drawing extensive attention both from industry and academia. Conventional …

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 …

LiDAR and camera are two important sensors for 3D object detection in autonomous driving.
Despite the increasing popularity of sensor fusion in this field, the robustness against inferior …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

Transformers have recently shown superior performances on various vision tasks. The large,
sometimes even global, receptive field endows Transformer models with higher …

Convolution and self-attention are two powerful techniques for representation learning, and
they are usually considered as two peer approaches that are distinct from each other. In this …

We propose 3DETR, an end-to-end Transformer based object detection model for 3D point
clouds. Compared to existing detection methods that employ a number of 3D-specific …

Abstract We present Voxel Transformer (VoTr), a novel and effective voxel-based
Transformer backbone for 3D object detection from point clouds. Conventional 3D …

Transformer, an attention-based encoder–decoder model, has already revolutionized the
field of natural language processing (NLP). Inspired by such significant achievements, some …

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to
input scene size is significantly smaller compared to 2D detection cases. Overlooking this …