FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

Abstract

Recently, promising applications in robotics and augmented reality have attracted considerable attention to 3D object detection from point clouds. In this paper, we present FCAF3D -- a first-in-class fully convolutional anchor-free indoor 3D object detection method. It is a simple yet effective method that uses a voxel representation of a point cloud and processes voxels with sparse convolutions. FCAF3D can handle large-scale scenes with minimal runtime through a single fully convolutional feed-forward pass. Existing 3D object detection methods make prior assumptions on the geometry of objects, and we argue that it limits their generalization ability. To eliminate prior assumptions, we propose a novel parametrization of oriented bounding boxes that allows obtaining better results in a purely data-driven way. The proposed method achieves state-of-the-art 3D object detection results in terms of [email protected] on ScanNet V2 (+4.5), SUN RGB-D (+3.5), and S3DIS (+20.5) datasets.The code and models are available at https://github.com/samsunglabs/fcaf3d

Cite

Text

Rukhovich et al. "FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-20080-9_28

Markdown

[Rukhovich et al. "FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/rukhovich2022eccv-fcaf3d/) doi:10.1007/978-3-031-20080-9_28

BibTeX

@inproceedings{rukhovich2022eccv-fcaf3d,
  title     = {{FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection}},
  author    = {Rukhovich, Danila and Vorontsova, Anna and Konushin, Anton},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2022},
  doi       = {10.1007/978-3-031-20080-9_28},
  url       = {https://mlanthology.org/eccv/2022/rukhovich2022eccv-fcaf3d/}
}