Abstract | ||
---|---|---|
Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors. These two-stage detectors improve with the accuracy of the intermediate depth estimation network, which can itself be improved without manual labels via large-scale self-supervised learning. However, they tend to suffer from overfitting more than end-to-end methods, are more complex, and the gap with similar lidar-based detectors remains significant. In this work, we propose an end-to-end, single stage, monocular 3D object detector, DD3D, that can benefit from depth pre-training like pseudo-lidar methods, but without their limitations. Our architecture is designed for effective information transfer between depth estimation and 3D detection, allowing us to scale with the amount of unlabeled pre-training data. Our method achieves state-of-the-art results on two challenging benchmarks, with 16.34% and 9.28% AP for Cars and Pedestrians (respectively) on the KITTI-3D benchmark, and 41.5% mAP on NuScenes. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCV48922.2021.00313 | ICCV |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dennis Park | 1 | 0 | 0.68 |
Rares Ambrus | 2 | 0 | 1.01 |
Vitor Guizilini | 3 | 0 | 1.69 |
Jie Li | 4 | 37 | 5.02 |
Adrien Gaidon | 5 | 0 | 0.34 |