Deep Portrait Delighting

We present a deep neural network for removing undesirable shading features from an unconstrained portrait image, recovering the underlying texture. Our training scheme incorporates three regularization strategies: masked loss, to emphasize high-frequency shading features; soft-shadow loss, which imp...

Full description

Saved in:
Bibliographic Details
Main Authors Weir, Joshua, Zhao, Junhong, Chalmers, Andrew, Rhee, Taehyun
Format Journal Article
LanguageEnglish
Published 22.03.2022
Subjects
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Online AccessGet full text

Cover

More Information
Summary:We present a deep neural network for removing undesirable shading features from an unconstrained portrait image, recovering the underlying texture. Our training scheme incorporates three regularization strategies: masked loss, to emphasize high-frequency shading features; soft-shadow loss, which improves sensitivity to subtle changes in lighting; and shading-offset estimation, to supervise separation of shading and texture. Our method demonstrates improved delighting quality and generalization when compared with the state-of-the-art. We further demonstrate how our delighting method can enhance the performance of light-sensitive computer vision tasks such as face relighting and semantic parsing, allowing them to handle extreme lighting conditions.
DOI:10.48550/arxiv.2203.12088