Deep Portrait Delighting
This addresses the challenge of handling extreme lighting conditions in portrait-based computer vision tasks like face relighting and semantic parsing, representing an incremental advancement.
The paper tackles the problem of removing undesirable shading from portrait images to recover underlying texture, achieving improved delighting quality and generalization compared to state-of-the-art methods.
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.