Work

Deep Shading: Convolutional Neural Networks for Screen Space Shading

Year: 2017

Type: article

Abstract: 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.

Source: Computer Graphics Forum

DOI: 10.1111/cgf.13225

Authors: O. Nalbach, E. Arabadzhiyska, D. Mehta, H.‐P. Seidel, T. Ritschel

Institutions: Max Planck Institute for Informatics, Saarland University, University College London

Language: English

Topic: Computer Graphics and Visualization Techniques

Subfield: Computer Graphics and Computer-Aided Design

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2311236754

FWCI: 33.21

Cites: 53

Cited by: 131

Related to: 10