Deep Shading: Convolutional Neural Networks for Screen-Space Shading

TL;DR

This paper introduces Deep Shading, a CNN-based method that learns to generate realistic screen-space shading effects from per-pixel attributes, improving visual quality and efficiency without manual programming.

Contribution

It presents a novel CNN approach for screen-space shading that learns effects directly from example images, bypassing manual shader programming.

Findings

Achieves competitive quality in screen-space effects

Runs efficiently in real-time applications

Learns complex shading effects from data

Abstract

In computer vision, convolutional neural networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen-space shading has recently increased the visual quality in interactive image synthesis, where per-pixel attributes such as positions, normals or reflectance of a virtual 3D scene are converted into RGB pixel appearance, enabling effects like ambient occlusion, indirect light, scattering, depth-of-field, motion blur, or anti-aliasing. In this paper we consider the diagonal problem: synthesizing appearance from given per-pixel attributes using a CNN. The resulting Deep Shading simulates various screen-space effects at competitive quality and speed while not being programmed by human experts but learned from example images.