Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification

Albert Mosella-Montoro, Javier Ruiz Hidalgo

ICCVW 2019 pp. 4123-4132

doi:10.1109/ICCVW.2019.00507 /iccvw/2019/mosellamontoro2019iccvw-residual/

Abstract

Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible errors due to missing local geometric context in the depth channel. This work proposes a novel Residual Attention Graph Convolutional Network that exploits the intrinsic geometric context inside a 3D space without using any kind of point features, allowing the use of organized or unorganized 3D data. Experiments are done in NYU Depth v1 and SUN-RGBD datasets to study the different configurations and to demonstrate the effectiveness of the proposed method. Experimental results show that the proposed method outperforms current state-of-the-art in geometric 3D scene classification tasks.

PDF ICCVW Semantic Scholar

Cite

Text

Mosella-Montoro and Hidalgo. "Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00507

Markdown

[Mosella-Montoro and Hidalgo. "Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/mosellamontoro2019iccvw-residual/) doi:10.1109/ICCVW.2019.00507

BibTeX

@inproceedings{mosellamontoro2019iccvw-residual,
  title     = {{Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification}},
  author    = {Mosella-Montoro, Albert and Hidalgo, Javier Ruiz},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {4123-4132},
  doi       = {10.1109/ICCVW.2019.00507},
  url       = {https://mlanthology.org/iccvw/2019/mosellamontoro2019iccvw-residual/}
}