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 …

In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

Fusing the camera and LiDAR information has become a de-facto standard for 3D object
detection tasks. Current methods rely on point clouds from the LiDAR sensor as queries to …

Autonomous driving perceives its surroundings for decision making, which is one of the most
complex scenarios in visual perception. The success of paradigm innovation in solving the …

Single frame data contains finite information which limits the performance of the existing
vision-based multi-camera 3D object detection paradigms. For fundamentally pushing the …

Recognizing scenes and objects in 3D from a single image is a longstanding goal of
computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets …

Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D
detection has brought significant improvement, eg, Pseudo-LiDAR methods. However, the …

Monocular 3D object detection aims to localize 3D bounding boxes in an input single 2D
image. It is a highly challenging problem and remains open, especially when no extra …

3D object detection from images, one of the fundamental and challenging problems in
autonomous driving, has received increasing attention from both industry and academia in …

Modern neural networks use building blocks such as convolutions that are equivariant to
arbitrary 2 D translations. However, these vanilla blocks are not equivariant to arbitrary 3 D …