"Single Photograph Surface Appearance Modeling with Self-Augmented CNNs and Inexact Supervision"
Wenjie Ye, Xiao Li, Yue Dong, Pieter Peers, and Xin Tong

Computer Graphics Forum, Volume 37, Issue 7, Oct 2018
This paper presents a deep learning based method for estimating the spatially varying surface reflectance properties from a single image of a planar surface under unknown natural lighting trained using only photographs of exemplar materials without referencing any artist generated or densely measured spatially varying surface reflectance training data. Our method is based on an empirical study of Li et al.'s [LDPT17] self-augmentation training strategy that shows that the main role of the initial approximative network is to provide guidance on the inherent ambiguities in single image appearance estimation. Furthermore, our study indicates that this initial network can be inexact (i.e., trained from other data sources) as long as it resolves the inherent ambiguities. We show that the single image estimation network trained without manually labeled data outperforms prior work in terms of accuracy as well as generality.

Supplementary Material
author = {Ye, Wenjie and Li, Xiao and Dong, Yue and Peers, Pieter and Tong, Xin},
title = {Single Photograph Surface Appearance Modeling with Self-Augmented {CNNs} and Inexact Supervision},
month = {Oct},
year = {2018},
journal = {Computer Graphics Forum},
volume = {37},
number = {7},
doi = {https://doi.org/10.1111/cgf.13560},