EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection

Tengteng Huang, Zhe Liu, Xiwu Chen, Xiang Bai

ECCV 2020

doi:10.1007/978-3-030-58555-6_3 /eccv/2020/huang2020eccv-epnet/

Abstract

In this paper, we aim at addressing two critical issues in the 3D detection task, including the exploitation of multiple sensors (namely LiDAR point cloud and camera image), as well as the inconsistency between the localization and classification confidence. To this end, we propose a novel fusion module to enhance the point features with semantic image features in a point-wise manner. Besides, a consistence forcing loss is employed to explicitly encourage the consistency of both the localization and classification confidence. We design an end-to-end learnable framework named EPNet to integrate these two components. Extensive experiments on the KITTI and SUN-RGBD datasets demonstrate the superiority of EPNet over the state-of-the-art methods.

PDF ECCV Semantic Scholar

Cite

Text

Huang et al. "EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58555-6_3

Markdown

[Huang et al. "EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/huang2020eccv-epnet/) doi:10.1007/978-3-030-58555-6_3

BibTeX

@inproceedings{huang2020eccv-epnet,
  title     = {{EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection}},
  author    = {Huang, Tengteng and Liu, Zhe and Chen, Xiwu and Bai, Xiang},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58555-6_3},
  url       = {https://mlanthology.org/eccv/2020/huang2020eccv-epnet/}
}