GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data
This addresses the issue of false positives in 3D object detection for autonomous driving, particularly for vulnerable road users, but is incremental as it enhances existing detectors rather than proposing a new paradigm.
The paper tackles the problem of inaccurate confidence estimation in black-box 3D object detectors on LiDAR data by introducing GACE, which aggregates geometric cues to improve confidence scores, resulting in consistent performance gains across state-of-the-art detectors, especially for pedestrians and cyclists.
Widely-used LiDAR-based 3D object detectors often neglect fundamental geometric information readily available from the object proposals in their confidence estimation. This is mostly due to architectural design choices, which were often adopted from the 2D image domain, where geometric context is rarely available. In 3D, however, considering the object properties and its surroundings in a holistic way is important to distinguish between true and false positive detections, e.g. occluded pedestrians in a group. To address this, we present GACE, an intuitive and highly efficient method to improve the confidence estimation of a given black-box 3D object detector. We aggregate geometric cues of detections and their spatial relationships, which enables us to properly assess their plausibility and consequently, improve the confidence estimation. This leads to consistent performance gains over a variety of state-of-the-art detectors. Across all evaluated detectors, GACE proves to be especially beneficial for the vulnerable road user classes, i.e. pedestrians and cyclists.