Deep Shading: Convolutional Neural Networks for Screen Space Shading

In computer vision, convolutional neural networks (CNNs) achieve unprecedented performance for inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen space shading has boosted the quality of real‐time rendering, con...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum 2017-07, Vol.36 (4), p.65-78
Main Authors: Nalbach, O., Arabadzhiyska, E., Mehta, D., Seidel, H.‐P., Ritschel, T.
Format: Article
Language:English
Subjects:
CCS Concepts
Computer graphics
Computer vision
Computing methodologies → Neural networks
Hardware reviews
Inverse problems
Neural networks
Occlusion
Pixels
Rasterization
Real time
Reflectance
Rendering
Scattering
Shading
Virtual reality
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In computer vision, convolutional neural networks (CNNs) achieve unprecedented performance for inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen space shading has boosted the quality of real‐time rendering, converting the same kind of attributes of a virtual scene back to appearance, enabling effects like ambient occlusion, indirect light, scattering and many more. In this paper we consider the diagonal problem: synthesizing appearance from given per‐pixel attributes using a CNN. The resulting Deep Shading renders screen space effects at competitive quality and speed while not being programmed by human experts but learned from example images.
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.13225