Meny

Javascript verkar inte påslaget? - Vissa delar av Lunds universitets webbplats fungerar inte optimalt utan javascript, kontrollera din webbläsares inställningar.
Du är här

Examensarbetspresentation Alexander Hansson och Peter Moodie

Seminarium
Classification of GPU rendering errors with Artifical Neural (Klassificering av GPU-renderingsfel med hjälp av artificiella neurala nätverk)

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 eval-
uation. 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.

Supervisors:
Magnus Oskarsson, Centre for Mathematical Sciences, Lund University
  Examiner Mikael Nilsson, Centre for Mathematical Sciences, Lund University
Tid: 
2019-06-10 10:15
Plats: 
MH:309A

Om händelsen

Tid: 
2019-06-10 10:15
Plats: 
MH:309A

Box 117, 221 00 LUND
Telefon 046-222 00 00 (växel)
Telefax 046-222 47 20
lu [at] lu [dot] se

Fakturaadress: Box 188, 221 00 LUND
Organisationsnummer: 202100-3211
Om webbplatsen