Fast Attention-Based Simplification of LiDAR Point Clouds for Object Detection and Classification
This method addresses the computational cost and power consumption of dense LiDAR point clouds for real-time object detection and classification in autonomous driving, offering a more efficient alternative to existing sampling methods.
This paper proposes an efficient learned point cloud simplification method for LiDAR data, combining a feature embedding module with an attention-based sampling module. The method was consistently faster than Farthest Point Sampling (FPS) and achieved similar or better accuracy on 3D object detection on KITTI and object classification across four datasets, especially under aggressive downsampling.
LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables accurate perception, it also increases computational cost and power consumption, which can limit real-time deployment. Existing point cloud sampling methods typically face a trade-off: very fast approaches tend to reduce accuracy, while more accurate methods are computationally expensive. To address this limitation, we propose an efficient learned point cloud simplification method for LiDAR data. The method combines a feature embedding module with an attention-based sampling module to prioritize task-relevant regions and is trained end-to-end. We evaluate the method against farthest point sampling (FPS) and random sampling (RS) on 3D object detection on the KITTI dataset and on object classification across four datasets. The method was consistently faster than FPS and achieved similar, and in some settings better, accuracy, with the largest gains under aggressive downsampling. It was slower than RS, but it typically preserved accuracy more reliably at high sampling ratios.