ML Anthology

Multi-Task Multi-Sensor Fusion for 3D Object Detection

Ming Liang, Bin Yang, Yun Chen, Rui Hu, Raquel Urtasun
CVPR 2019
doi:10.1109/CVPR.2019.00752 /cvpr/2019/liang2019cvpr-multitask/

Abstract

In this paper we propose to exploit multiple related tasks for accurate multi-sensor 3D object detection. Towards this goal we present an end-to-end learnable architecture that reasons about 2D and 3D object detection as well as ground estimation and depth completion. Our experiments show that all these tasks are complementary and help the network learn better representations by fusing information at various levels. Importantly, our approach leads the KITTI benchmark on 2D, 3D and bird's eye view object detection, while being real-time.

PDF CVPR Semantic Scholar

Cite

Text

Liang et al. "Multi-Task Multi-Sensor Fusion for 3D Object Detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00752

Markdown

[Liang et al. "Multi-Task Multi-Sensor Fusion for 3D Object Detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/liang2019cvpr-multitask/) doi:10.1109/CVPR.2019.00752

BibTeX

@inproceedings{liang2019cvpr-multitask,
  title     = {{Multi-Task Multi-Sensor Fusion for 3D Object Detection}},
  author    = {Liang, Ming and Yang, Bin and Chen, Yun and Hu, Rui and Urtasun, Raquel},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00752},
  url       = {https://mlanthology.org/cvpr/2019/liang2019cvpr-multitask/}
}