NeRF as super-resolution method

Simple item page
dc.contributor.advisorvan Bergen, R.S.
dc.contributor.advisorKietzmann, T.C.
dc.contributor.authorBerberich, Sven
dc.date.issued2021-06-18
dc.description.abstractThis thesis is concerning itself with the question whether Neural radiance elds (NeRF) can be used to perform super-resolution. The NeRF method learns a scene representation by receiving images of said scene to train on. As this representation receives information from multiple images we hy- pothesise that the learned representation contains more information than a single image does and could thus create accurate high-resolution outputs while only training on low-resolution images. We observe that the creation of HR images is quite possible, the quality of these is however, only in very limited situations, comparable with interpo- lation based super-resolution methods and signi cantly worse then state-of- the-art methods.en_US
dc.identifier.urihttps://theses.ubn.ru.nl/handle/123456789/12759
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationBachelor Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeBacheloren_US
dc.titleNeRF as super-resolution methoden_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Berberich, S. s-1006248-BSc-Thesis-2021.pdf
Size:
4.21 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculteit der Sociale Wetenschappen