GBlobs: Local LiDAR Geometry for Improved Sensor Placement Generalization
This addresses generalization issues in LiDAR-based 3D object detection for autonomous driving applications, representing a strong specific improvement.
The paper tackles the problem of 3D object detectors relying on absolute position rather than shape features, which limits generalization to different LiDAR sensor placements. Their solution, GBlobs, achieved state-of-the-art performance in the RoboSense 2025 challenge.
This technical report outlines the top-ranking solution for RoboSense 2025: Track 3, achieving state-of-the-art performance on 3D object detection under various sensor placements. Our submission utilizes GBlobs, a local point cloud feature descriptor specifically designed to enhance model generalization across diverse LiDAR configurations. Current LiDAR-based 3D detectors often suffer from a \enquote{geometric shortcut} when trained on conventional global features (\ie, absolute Cartesian coordinates). This introduces a position bias that causes models to primarily rely on absolute object position rather than distinguishing shape and appearance characteristics. Although effective for in-domain data, this shortcut severely limits generalization when encountering different point distributions, such as those resulting from varying sensor placements. By using GBlobs as network input features, we effectively circumvent this geometric shortcut, compelling the network to learn robust, object-centric representations. This approach significantly enhances the model's ability to generalize, resulting in the exceptional performance demonstrated in this challenge.