View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis
By Xin Wei, Ruixuan Yu. Computer Vision and Pattern Recognition, 2020
324 citations recorded by the source corpus.
View-based approach that recognizes 3D shape through its projected 2D images has achieved state-of-the-art results for 3D shape recognition. The major challenge for view-based approach is how to aggregate multi-view features to be a global shape descriptor. In this work, we propose a novel view-based Graph Convolutional Neural Network, dubbed as view-GCN, to recognize 3D shape based on graph representation of multiple views in flexible view configurations. We first construct view-graph with multiple views as graph nodes, then design a graph convolutional neural network over view-graph to hierarchically learn discriminative shape descriptor considering relations of multiple views. The view-GCN is a hierarchical network based on local and non-local graph convolution for feature transform, and selective view-sampling for graph coarsening. Extensive experiments on benchmark datasets show that view-GCN achieves state-of-the-art results for 3D shape classification and retrieval.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/e88a794a5c2313fb6ab8d8a1372624106cd83bb4
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- Ali K. Thabet
- Bing Li
- Silvio Giancola
- Abdullah Hamdi
- Bernard Ghanem
- Zahra Kadkhodaie
- Eero P. Simoncelli
In Computer Vision and Pattern Recognition
- Ali K. Thabet
- Bernard Ghanem
- Silvio Giancola
- Bing Li
- Abdullah Hamdi
- Luc Van Gool
- Martin Danelljan
- Ming-Hsuan Yang
Citations in the corpus
- Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence (2023, methodology): “[98] proposed a model named View-GCN which can 3D shape based on a graph representation of multiple views infexible view confguration.”
- MVTN: Multi-View Transformation Network for 3D Shape Recognition (2020, methodology): “Note in Table 1 how our MVTN improves the previous state-of-the-art in classification (ViewGCN [32]) when tested on the same setup.”