liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Compressive Image Reconstruction in Reduced Union of Subspaces
Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten. (Computer Graphics and Image Processing)
Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten. (Computer Graphics and Image Processing)
Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten. (Computer Graphics and Image Processing)ORCID-id: 0000-0002-7765-1747
2015 (engelsk)Inngår i: Computer Graphics Forum, ISSN 1467-8659, Vol. 34, nr 2, s. 33-44Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

We present a new compressed sensing framework for reconstruction of incomplete and possibly noisy images and their higher dimensional variants, e.g. animations and light-fields. The algorithm relies on a learning-based basis representation. We train an ensemble of intrinsically two-dimensional (2D) dictionaries that operate locally on a set of 2D patches extracted from the input data. We show that one can convert the problem of 2D sparse signal recovery to an equivalent 1D form, enabling us to utilize a large family of sparse solvers. The proposed framework represents the input signals in a reduced union of subspaces model, while allowing sparsity in each subspace. Such a model leads to a much more sparse representation than widely used methods such as K-SVD. To evaluate our method, we apply it to three different scenarios where the signal dimensionality varies from 2D (images) to 3D (animations) and 4D (light-fields). We show that our method outperforms state-of-the-art algorithms in computer graphics and image processing literature.

sted, utgiver, år, opplag, sider
John Wiley & Sons Ltd , 2015. Vol. 34, nr 2, s. 33-44
Emneord [en]
Image reconstruction, compressed sensing, light field imaging
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-119639DOI: 10.1111/cgf.12539ISI: 000358326600008OAI: oai:DiVA.org:liu-119639DiVA, id: diva2:825377
Konferanse
Eurographics 2015
Prosjekter
VPS
Forskningsfinansiär
Swedish Foundation for Strategic Research , IIS11-0081Tilgjengelig fra: 2015-06-23 Laget: 2015-06-23 Sist oppdatert: 2018-11-23bibliografisk kontrollert
Inngår i avhandling
1. Sparse representation of visual data for compression and compressed sensing
Åpne denne publikasjonen i ny fane eller vindu >>Sparse representation of visual data for compression and compressed sensing
2018 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

The ongoing advances in computational photography have introduced a range of new imaging techniques for capturing multidimensional visual data such as light fields, BRDFs, BTFs, and more. A key challenge inherent to such imaging techniques is the large amount of high dimensional visual data that is produced, often requiring GBs, or even TBs, of storage. Moreover, the utilization of these datasets in real time applications poses many difficulties due to the large memory footprint. Furthermore, the acquisition of large-scale visual data is very challenging and expensive in most cases. This thesis makes several contributions with regards to acquisition, compression, and real time rendering of high dimensional visual data in computer graphics and imaging applications.

Contributions of this thesis reside on the strong foundation of sparse representations. Numerous applications are presented that utilize sparse representations for compression and compressed sensing of visual data. Specifically, we present a single sensor light field camera design, a compressive rendering method, a real time precomputed photorealistic rendering technique, light field (video) compression and real time rendering, compressive BRDF capture, and more. Another key contribution of this thesis is a general framework for compression and compressed sensing of visual data, regardless of the dimensionality. As a result, any type of discrete visual data with arbitrary dimensionality can be captured, compressed, and rendered in real time.

This thesis makes two theoretical contributions. In particular, uniqueness conditions for recovering a sparse signal under an ensemble of multidimensional dictionaries is presented. The theoretical results discussed here are useful for designing efficient capturing devices for multidimensional visual data. Moreover, we derive the probability of successful recovery of a noisy sparse signal using OMP, one of the most widely used algorithms for solving compressed sensing problems.

sted, utgiver, år, opplag, sider
Linköping: Linköping University Electronic Press, 2018. s. 158
Serie
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 1963
HSV kategori
Identifikatorer
urn:nbn:se:liu:diva-152863 (URN)10.3384/diss.diva-152863 (DOI)9789176851869 (ISBN)
Disputas
2018-12-14, Domteatern, Visualiseringscenter C, Kungsgatan 54, Campus Norrköping, Norrköping, 09:15 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2018-11-23 Laget: 2018-11-23 Sist oppdatert: 2018-11-23bibliografisk kontrollert

Open Access i DiVA

fulltext(39942 kB)32 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 39942 kBChecksum SHA-512
41919e41b35c02ef1aaef17b0d2139c647ae44db02cb56aa6fc44073367672fad2f6e17781627dac8ecc13bcea632e3a3274b5e20f2781ad8abd096fef5dc496
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstProject web page

Personposter BETA

Miandji, EhsanKronander, JoelUnger, Jonas

Søk i DiVA

Av forfatter/redaktør
Miandji, EhsanKronander, JoelUnger, Jonas
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 32 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 400 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf