Corpus ID: 9075218

3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks

@article{Ren20173DANets3D,
  title={3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks},
  author={Mengwei Ren and Liang Niu and Y. Fang},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.10108}
}

• Mengwei Ren, Liang Niu, Y. Fang
• Published 2017
• Computer Science
• ArXiv

Recently researchers have been shifting their focus towards learned 3D shape descriptors from hand-craft ones to better address challenging issues of the deformation and structural variation inherently present in 3D objects. [...] Key Method We developed new definition of 2D multilayer dense representation (MDR) of 3D volumetric data to extract concise but geometrically informative shape description and a novel design of adversarial networks that jointly train a set of convolution neural network (CNN…Expand

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed