Abstract
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.
Originalsprache | englisch |
---|---|
Titel | Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV) |
Seiten | 6566-6576 |
Seitenumfang | 11 |
DOIs | |
Publikationsstatus | Veröffentlicht - 2023 |
Veranstaltung | 2023 IEEE/CVF International Conference on Computer Vision: ICCV 2023 - Paris, Frankreich Dauer: 1 Okt. 2023 → 6 Okt. 2023 |
Konferenz
Konferenz | 2023 IEEE/CVF International Conference on Computer Vision |
---|---|
Kurztitel | ICCV 2023 |
Land/Gebiet | Frankreich |
Ort | Paris |
Zeitraum | 1/10/23 → 6/10/23 |
ASJC Scopus subject areas
- Maschinelles Sehen und Mustererkennung