Detailed info
Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?
| Authors | Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Elisa Ricci |
| Title | Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection? |
| Abstract | Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the commonly reported validation split. This generated a distorted impression about the superiority of Pseudo-LiDAR-based (PLbased) approaches over methods working with RGB images only. Our first contribution consists in rectifying this view by pointing out and showing experimentally that the validation results published by PL-based methods are substantially biased. The source of the bias resides in an overlap between the KITTI3D object detection validation set and the training/validation sets used to train depth predictors feeding PL-based methods. Surprisingly, the bias remains also after geographically removing the overlap. This leaves the test set as the only reliable set for comparison, where published PL-based methods do not excel. Our second contribution brings PL-based methods back up in the ranking with the design of a novel deep architecture which introduces a 3D confidence prediction module. We show that 3D confidence estimation techniques derived from RGB-only 3Ddetection approaches can be successfully integrated into our framework and, more importantly, that improved performance can be obtained with a newly designed 3D confidence measure, leading to state-of-the-art performance on the KITTI3D benchmark. |
| ISBN | Ν/Α |
| Conference | International Conference on Computer Vision 2021 |
| Date | 11-17/10/2021 |
| Location | virtually |
| Year of Publication, Publisher | 2021 |
| Url | https://zenodo.org/record/5795266 |
| DOI | 10.5281/zenodo.5795266 |
Menu
- Home
- About
- Experimentation
- Knowledge Hub
- ContactResults
- News & Events
- Contact
Funding
This project has received funding from the European Union’s Horizon 2020 Research and Innovation program under grant agreement No 957337. The website reflects only the view of the author(s) and the Commission is not responsible for any use that may be made of the information it contains.
