Neural Network Ambient Occlusion

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publicationSA '16 SIGGRAPH ASIA 2016 Technical Briefs
PublisherACM
Number of pages4
ISBN (Electronic)978-1-4503-4541-5
DOIs
Publication statusPublished - 28 Nov 2016
EventSIGGRAPH ASIA 2016 Technical Briefs - , Macao
Duration: 5 Dec 20168 Dec 2016
https://sa2016.siggraph.org/

Conference

ConferenceSIGGRAPH ASIA 2016 Technical Briefs
Abbreviated titleSA'16
Country/TerritoryMacao
Period5/12/168/12/16
Internet address

Keywords / Materials (for Non-textual outputs)

  • Neural Networks
  • Machine learning
  • screen space ambient occlusion
  • SSAO
  • HABA

Fingerprint

Dive into the research topics of 'Neural Network Ambient Occlusion'. Together they form a unique fingerprint.

Cite this