LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are
usually implemented in specialized networks with distinctive architectures that are difficult to …

State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud
semantic segmentation, panoptic segmentation and 3D detection, etc.) often project the …

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the
point clouds to 2D space and then process them via 2D convolution. Although this …

At the heart of all automated driving systems is the ability to sense the surroundings, eg,
through semantic segmentation of LiDAR sequences, which experienced a remarkable …

In this work, we present a new paradigm, called 4D-StOP, to tackle the task of 4D Panoptic
LiDAR Segmentation. 4D-StOP first generates spatio-temporal proposals using voting …

Abstract 3D LiDAR (light detection and ranging) semantic segmentation is important in
scene understanding for many applications, such as auto-driving and robotics. For example …

Recent advances in 2D CNNs and vision transformers (ViTs) reveal that large kernels are
essential for enough receptive fields and high performance. Inspired by this literature, we …

With the rapid advances in autonomous driving, it becomes critical to equip its sensing
system with more holistic 3D perception. However, widely explored tasks like 3D detection …

Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the
cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from …

Autonomous robotic systems and self driving cars rely on accurate perception of their
surroundings as the safety of the passengers and pedestrians is the top priority. Semantic …