DeepFlash: Turning a Flash Selfie into a Studio Portrait
This addresses the issue of poor lighting in smartphone selfies for general users, but it is incremental as it applies existing neural network methods to a specific photography task.
The paper tackles the problem of converting flash selfies into studio-quality portraits by correcting defects like specular highlights and shadows, achieving results that mimic uniform studio lighting.
We present a method for turning a flash selfie taken with a smartphone into a photograph as if it was taken in a studio setting with uniform lighting. Our method uses a convolutional neural network trained on a set of pairs of photographs acquired in an ad-hoc acquisition campaign. Each pair consists of one photograph of a subject's face taken with the camera flash enabled and another one of the same subject in the same pose illuminated using a photographic studio-lighting setup. We show how our method can amend defects introduced by a close-up camera flash, such as specular highlights, shadows, skin shine, and flattened images.