SVBRDFNet

Implementation of the CNN described in Xiao Li, Yue Dong, Pieter Peers, Xin Tong. Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks. ACM Trans. Grp. 36, 4 (July 2017), 45:1-45:11 in tensorflow, following their original implementation in caffe. Some utilities and the rendering engine remains unchanged as provided in the source codes. See their project page http://msraig.info/~sanet/sanet.htm for more information.