![Deep Portrait Delighting](https://i0.wp.com/papercopilot.com/wp-content/uploads/2022/11/deep-portrait-delighting.png?resize=800%2C800&ssl=1)
Joshua Weir, Junhong Zhao, Andrew Chalmers, Taehyun Rhee
Victoria University of Wellington
Portals
Abstract
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.