# Plausible Shading Decomposition For Layered Photo Retouching

## TL;DR

This paper introduces a neural network-based system for decomposing a single image into layered shading components like shadow and specular effects, enabling advanced photo editing that was previously difficult from a single photo.

## Contribution

We propose a novel plausible shading decomposition method using neural networks trained on synthetic data, applicable to real photographs for enhanced photo manipulation.

## Key findings

- Effective decomposition on synthetic and real images
- Enables complex photo manipulations from single images
- Outperforms existing methods in plausibility and utility

## Abstract

Photographers routinely compose multiple manipulated photos of the same scene (layers) into a single image, which is better than any individual photo could be alone. Similarly, 3D artists set up rendering systems to produce layered images to contain only individual aspects of the light transport, which are composed into the final result in post-production. Regrettably, both approaches either take considerable time to capture, or remain limited to synthetic scenes. In this paper, we suggest a system to allow decomposing a single image into a plausible shading decomposition (PSD) that approximates effects such as shadow, diffuse illumination, albedo, and specular shading. This decomposition can then be manipulated in any off-the-shelf image manipulation software and recomposited back. We perform such a decomposition by learning a convolutional neural network trained using synthetic data. We demonstrate the effectiveness of our decomposition on synthetic (i.e., rendered) and real data (i.e., photographs), and use them for common photo manipulation, which are nearly impossible to perform otherwise from single images.