Single Image Surface Appearance Modeling with Self‐augmented CNNs and Inexact Supervision. (24th October 2018)

• Record Type: Journal Article
• Authors: Ye, Wenjie; Li, Xiao; Dong, Yue; Peers, Pieter; Tong, Xin
• Is Part Of: Computer graphics forum. Volume 37:Number 7(2018)
• Page Start: 201
• Page End: 211
• Publication Date: 2018-10-24
• Subjects: CCS Concepts -- Computing methodologies → Reflectance modeling; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.13560
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: 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.