Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Classification of GPU rendering errors with Artificial Neural Networks

Hansson, Alexander LU and Moodie, Peter (2019) In Master's Theses in Mathematical Sciences FMAM05 20191
Mathematics (Faculty of Engineering)
Abstract (Swedish)
Image quality metrics are used to evaluate the percieved quality of processed images. Differences in hardware between graphics processors contribute to noise during quality evaluation. In this masters thesis paper we train and evaluate neural networks as metrics to evaluate GPU rendering quality. The neural networks can successfully ignore the rendering noise that occurs when the test and reference frames are rendered by different GPUs. This reduces tedious human interaction which requires manual updates of reference-frames during quality testing.
Please use this url to cite or link to this publication:
author
Hansson, Alexander LU and Moodie, Peter
supervisor
organization
course
FMAM05 20191
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Machine learning, Artificial Neural Networks, Image Analysis, Image quality metrics, Graphics processors, Quality testing
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3386-2019
ISSN
1404-6342
other publication id
2019:E30
language
English
id
8981960
date added to LUP
2019-07-16 13:35:54
date last changed
2019-07-16 13:35:54
@misc{8981960,
  abstract     = {{Image quality metrics are used to evaluate the percieved quality of processed images. Differences in hardware between graphics processors contribute to noise during quality evaluation. In this masters thesis paper we train and evaluate neural networks as metrics to evaluate GPU rendering quality. The neural networks can successfully ignore the rendering noise that occurs when the test and reference frames are rendered by different GPUs. This reduces tedious human interaction which requires manual updates of reference-frames during quality testing.}},
  author       = {{Hansson, Alexander and Moodie, Peter}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master's Theses in Mathematical Sciences}},
  title        = {{Classification of GPU rendering errors with Artificial Neural Networks}},
  year         = {{2019}},
}