Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
LEARNING SCENE SPECIFIC RECONSTRUCTION OF MONTE CARLO PATH TRACED IMAGE SEQUENCES WITHOUT ADDITIONAL CLEAN DATA
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

When using deep learning models for reconstruction of one path per pixel Monte Carlo path traced image sequences, reconstruction of unseen features can be a concern. Th‘is can be solved by training the model on the same scene it is supposed to reconstruct images from. Learning to specialize with additional clean targets would be extremely time consuming, instead training with additional noisy targets saves time as additional noisy images is tremendously faster to render. ‘This thesis shows that a model trained without clean targets on the same scene it is reconstructing images from can under certain conditions out performa model trained on clean targets from diff‚erent scenes. It also shows that €first training a model on clean targets followed by noisy targets can help with instability issues one can encounter when only training with noisy targets. Lastly, the thesis shows how there is not much of an improvement going from 400 to 1000 training examples or going from noisy targets rendered with one path per pixel to targets rendered with eight paths per pixel.

Place, publisher, year, edition, pages
2019. , p. 38
Series
UMNAD ; 1203
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:umu:diva-164719OAI: oai:DiVA.org:umu-164719DiVA, id: diva2:1366352
Educational program
Master of Science Programme in Computing Science and Engineering
Supervisors
Examiners
Available from: 2019-10-29 Created: 2019-10-29 Last updated: 2019-10-29Bibliographically approved

Open Access in DiVA

fulltext(39335 kB)5 downloads
File information
File name FULLTEXT01.pdfFile size 39335 kBChecksum SHA-512
01d4d62fc70006bd617284e88fb225a29f08fa80bc377212c22d8b41f0ca0aaed1f1b8727f7f0d528677188426396770f51fe791c1d479bd86e5b960b6c88e7d
Type fulltextMimetype application/pdf

By organisation
Department of Computing Science
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 5 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 60 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf