English

Is Pseudo-Lidar needed for Monocular 3D Object detection?

Computer Vision and Pattern Recognition 2021-08-17 v1

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.

Keywords

Cite

@article{arxiv.2108.06417,
  title  = {Is Pseudo-Lidar needed for Monocular 3D Object detection?},
  author = {Dennis Park and Rares Ambrus and Vitor Guizilini and Jie Li and Adrien Gaidon},
  journal= {arXiv preprint arXiv:2108.06417},
  year   = {2021}
}

Comments

In Proceedings of the ICCV 2021

R2 v1 2026-06-24T05:06:28.434Z