This is a modified version of the Caffe deep learning framework to be used for working with the networks presented in our Deep Shading paper.
This modification is based on the official Caffe source of Aug 10, 2016. It contains two additional loss layers (L1 and SSIM-based loss) and enables the use of image sets in the EXR format.
Caffe is released under the BSD 2-Clause license. The BVLC reference models are released for unrestricted use.