Neural network ambient occlusion
Authors:
Open Access
- 28 November 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Abstract
We present Neural Network Ambient Occlusion (NNAO), a fast, accurate screen space ambient occlusion algorithm that uses a neural network to learn an optimal approximation of the ambient occlusion effect. Our network is carefully designed such that it can be computed in a single pass allowing it to be used as a drop-in replacement for existing screen space ambient occlusion techniques.Keywords
Funding Information
- Marza Animation Planet (-)
This publication has 9 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- A machine learning approach for filtering Monte Carlo noiseACM Transactions on Graphics, 2015
- Image based relighting using neural networksACM Transactions on Graphics, 2015
- Unreal Engine 4 Elemental2012
- The alchemy screen-space ambient obscurance algorithm2011
- CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of PhotographsIEEE Transactions on Visualization and Computer Graphics, 2010
- Effects & techniques2008
- Image-space horizon-based ambient occlusion2008
- Finding next gen2007