# DeepFlash: Turning a Flash Selfie into a Studio Portrait

## TL;DR

This paper introduces DeepFlash, a neural network-based method that transforms smartphone flash selfies into studio-quality portraits by correcting lighting and skin appearance issues.

## Contribution

DeepFlash is a novel neural network approach trained on paired flash and studio-lit images to enhance smartphone selfies to studio quality.

## Key findings

- Effectively removes flash artifacts like highlights and shadows.
- Produces images with more uniform lighting and natural skin appearance.
- Demonstrates significant improvement over unprocessed flash selfies.

## Abstract

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.