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

LiDAR-based 3D point cloud recognition has benefited various applications. Without
specially considering the LiDAR point distribution, most current methods suffer from …

Transformers have become one of the foundational architectures in point cloud analysis
tasks due to their excellent global modeling ability. However, the attention mechanism has …

False negatives (FN) in 3D object detection, eg, missing predictions of pedestrians, vehicles,
or other obstacles, can lead to potentially dangerous situations in autonomous driving. While …

Directly producing planning results from raw sensors has been a long-desired solution for
autonomous driving and has attracted increasing attention recently. Most existing end-to …

In the context of autonomous driving the significance of effective feature learning is widely
acknowledged. While conventional 3D self-supervised pre-training methods have shown …

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for
end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the …

We introduce a novel visual question answering (VQA) task in the context of autonomous
driving, aiming to answer natural language questions based on street-view clues. Compared …

Existing point cloud based 3D detectors are designed for the particular scene, either indoor
or outdoor ones. Because of the substantial differences in object distribution and point …

Segment anything model (SAM) developed by Meta AI Research has recently attracted
significant attention. Trained on a large segmentation dataset of over 1 billion masks, SAM is …