Code, pre-trained model and data for paper Neural Face Editing with Intrinsic Image Disentangling. [arxiv]
Part of our augmented CelebA (http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html) (hdf5 file, with cropped image, rough estimation of mask, normals, and spherical harmonics parameters) can be found at: [Google Drive].
If you use our code, please consider cite the following: Zhixin Shu, Ersin Yumer, Sunil Hadap, Kalyan Sunkavalli, Eli Shechtman, and Dimitris Samaras. Neural Face Editing with Intrinsic Image Disentangling. CVPR, 2017.
@inproceedings{NeuralFace2017,
title = {Neural Face Editing with Intrinsic Image Disentangling},
author = {Shu, Z., and Yumer, E., and Hadap, S., and Sunkavalli, K., and Shechtman, E., and Samaras, D.},
booktitle={Computer Vision and Pattern Recognition, 2017. CVPR 2017. IEEE Conference on},
organization = {IEEE},
pages = {-},
year = {2017},
}