Header logo is ps

Convolutional Mesh Autoencoders

2018-09-08


The code allows to build convolutional networks on mesh structures analogous to CNNs on images. The code includes mesh convolutions, and introduces downsampling and upsampling operators that can be directly applied to the mesh structure. The code implements a Convolution Mesh Autoencoder using the above mesh processing operators and achieves state of the art results on generating 3D facial meshes.

Author(s): Anurag Ranjan and Timo Bolkart and Soubhik Sanyal and Michael J. Black
Department(s): Perceiving Systems
Publication(s): Generating {3D} Faces using Convolutional Mesh Autoencoders
Authors: Anurag Ranjan and Timo Bolkart and Soubhik Sanyal and Michael J. Black
Maintainers: Anurag Ranjan and Timo Bolkart
Release Date: 2018-09-08
License: The MIT License (MIT)
Copyright: Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V.
Repository: https://github.com/anuragranj/coma
External Link: http://coma.is.tue.mpg.de/