Deep Continuous Fusion for Multi-Sensor 3D Object Detection

Abstract

In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization. Towards this goal, we design an end-to-end learnable architecture that exploits continuous convolutions to fuse image and LIDAR feature maps at different levels of resolution. Our proposed continuous fusion layer encode both discrete-state image features as well as continuous geometric information. This enables us to design a novel, reliable and efficient end-to-end learnable 3D object detector based on multiple sensors. Our experimental evaluation on both KITTI as well as a large scale 3D object detection benchmark shows significant improvements over the state of the art.

Cite

Text

Liang et al. "Deep Continuous Fusion for Multi-Sensor 3D Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01270-0_39

Markdown

[Liang et al. "Deep Continuous Fusion for Multi-Sensor 3D Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/liang2018eccv-deep/) doi:10.1007/978-3-030-01270-0_39

BibTeX

@inproceedings{liang2018eccv-deep,
  title     = {{Deep Continuous Fusion for Multi-Sensor 3D Object Detection}},
  author    = {Liang, Ming and Yang, Bin and Wang, Shenlong and Urtasun, Raquel},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01270-0_39},
  url       = {https://mlanthology.org/eccv/2018/liang2018eccv-deep/}
}