Deep Shading: Convolutional Neural Networks for Screen-Space Shading
This addresses the need for efficient and automated screen-space shading in computer graphics, offering a learned alternative to expert-designed methods.
The paper tackles the problem of synthesizing appearance from per-pixel attributes in screen-space shading using a convolutional neural network, achieving competitive quality and speed for effects like ambient occlusion and indirect light without manual programming.
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.