Lidar-Based 3D Object Detection
Overview
Lidar-based 3D object detection turns sparse, irregular point clouds into 3D bounding boxes and class labels, helping mobile systems understand nearby objects and their positions. Common approaches organize points as voxels or pillars, process them directly or in bird’s-eye-view grids, and use convolutional networks, transformers, or newer sequence models; some combine lidar with cameras, radar, or cooperative vehicle data. Current work also addresses long-range and rare-object detection, low-latency inference, adaptation across sensors and environments, and robustness to weather, corruption, and adversarial point changes. A central tension is improving accuracy under sparse or shifted data while keeping computation, sensing, and communication within practical limits.
Latest papers
63 papers11 papers in the last four weeks, up 120% on the four weeks before. 0.1% of all new papers.