Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification

  title={Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification},
  author={Albert Mosella-Montoro and J. Hidalgo},
  journal={2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)},
  • Albert Mosella-Montoro, J. Hidalgo
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
  • 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… CONTINUE READING
    1 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    2D-3D Geometric Fusion Network using Multi-Neighbourhood Graph Convolution for RGB-D Indoor Scene Classification
    • Highly Influenced
    • PDF


    RGB-D Scene Classification via Multi-modal Feature Learning
    • 5
    • Highly Influential
    3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation
    • 111
    • PDF
    3D Graph Neural Networks for RGBD Semantic Segmentation
    • 190
    • PDF
    ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
    • 720
    • PDF
    VoxNet: A 3D Convolutional Neural Network for real-time object recognition
    • Daniel Maturana, S. Scherer
    • Computer Science
    • 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • 2015
    • 1,481
    • PDF
    Unstructured Point Cloud Semantic Labeling Using Deep Segmentation Networks
    • 124
    • PDF
    FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
    • 144
    • Highly Influential
    • PDF
    SUN RGB-D: A RGB-D scene understanding benchmark suite
    • 691
    • PDF
    SEGCloud: Semantic Segmentation of 3D Point Clouds
    • 248
    • PDF