We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the
memory and computational cost, existing point-based pipelines usually adopt task-agnostic …

With the fast development of 3D data acquisition techniques, topographic point clouds have
become easier to acquire and have promoted many geospatial applications. Ground filtering …

With the rapid development of sensor technologies and the widespread use of laser
scanning equipment, point clouds, as the main data form and an important information …

Although various 3D datasets with different functions and scales have been proposed
recently, it remains challenging for individuals to complete the whole pipeline of large-scale …

Current 3D open-vocabulary scene understanding methods mostly utilize well-aligned 2D
images as the bridge to learn 3D features with language. However, applying these …

We study the problem of object detection in remote sensing images. As a simple but effective
feature extractor, Feature Pyramid Network (FPN) has been widely used in several generic …

Abstract Collaboration between Light Detection and Ranging (LiDAR) point clouds and
deep learning has been proven to be an effective approach for vegetation mapping. Current …

We present the UrbanBIS benchmark for large-scale 3D urban understanding, supporting
practical urban-level semantic and building-level instance segmentation. UrbanBIS …

LiDAR sensor is essential to the perception system in autonomous vehicles and intelligent
robots. To fulfill the real-time requirements in real-world applications, it is necessary to …

When using LiDAR semantic segmentation models for safety-critical applications such as
autonomous driving, it is essential to understand and improve their robustness with respect …