SurfNet: Generating 3D shape surfaces using deep residual networks

SurfNet: Generating 3D shape surfaces using deep residual networks

Sinha, A., Unmesh, A., Huang, Q., and Ramani, K
Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

  3D shape models are naturally parameterized using vertices and faces, i.e., composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a...