# Single Image Portrait Relighting

## TL;DR

This paper introduces a neural network system that can relight a single portrait photo taken with a cellphone in any environment, producing realistic lighting effects quickly and without specialized hardware.

## Contribution

The authors develop a neural network that performs portrait relighting from a single image in unconstrained settings, trained on a small, controlled dataset, and capable of real-time performance.

## Key findings

- Outperforms prior methods quantitatively on validation data.
- Produces convincing relighting results on real-world cellphone portraits.
- Operates in 160 milliseconds for 640x640 images.

## Abstract

Lighting plays a central role in conveying the essence and depth of the subject in a portrait photograph. Professional photographers will carefully control the lighting in their studio to manipulate the appearance of their subject, while consumer photographers are usually constrained to the illumination of their environment. Though prior works have explored techniques for relighting an image, their utility is usually limited due to requirements of specialized hardware, multiple images of the subject under controlled or known illuminations, or accurate models of geometry and reflectance. To this end, we present a system for portrait relighting: a neural network that takes as input a single RGB image of a portrait taken with a standard cellphone camera in an unconstrained environment, and from that image produces a relit image of that subject as though it were illuminated according to any provided environment map. Our method is trained on a small database of 18 individuals captured under different directional light sources in a controlled light stage setup consisting of a densely sampled sphere of lights. Our proposed technique produces quantitatively superior results on our dataset's validation set compared to prior works, and produces convincing qualitative relighting results on a dataset of hundreds of real-world cellphone portraits. Because our technique can produce a 640 $\times$ 640 image in only 160 milliseconds, it may enable interactive user-facing photographic applications in the future.