WangYueFt/dgcnn
Dynamic Graph CNN implementation for learning on 3D point clouds using EdgeConv neural network modules.
Not currently ranked — collecting fresh signals.
star history
DGCNN provides a re-implementation of the Dynamic Graph CNN architecture featuring EdgeConv, a differentiable neural network module designed for processing point clouds. The implementation supports high-level tasks including 3D object classification, semantic segmentation, and part segmentation. Both TensorFlow and PyTorch versions are provided, with the PyTorch implementation used for the original paper’s classification experiments. The model achieves state-of-the-art performance on point-cloud benchmarks and includes evaluations under corruption scenarios using ModelNet-C.
Frequently asked
- What is WangYueFt/dgcnn?
- Dynamic Graph CNN implementation for learning on 3D point clouds using EdgeConv neural network modules.
- Is dgcnn open source?
- Yes — WangYueFt/dgcnn is open source, released under the MIT license.
- What language is dgcnn written in?
- WangYueFt/dgcnn is primarily written in Python.
- How popular is dgcnn?
- WangYueFt/dgcnn has 1.8k stars on GitHub.
- Where can I find dgcnn?
- WangYueFt/dgcnn is on GitHub at https://github.com/WangYueFt/dgcnn.