Convolutional Sparse Coding for High Dynamic Range Imaging

Current HDR acquisition techniques are based on either (i) fusing multibracketed, low dynamic range (LDR) images, (ii) modifying existing hardware and capturing different exposures simultaneously with multiple sensors, or (iii) reconstructing a single image with spatially‐varying pixel exposures. In...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer graphics forum Ročník 35; číslo 2; s. 153 - 163
Hlavní autoři: Serrano, Ana, Heide, Felix, Gutierrez, Diego, Wetzstein, Gordon, Masia, Belen
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford Blackwell Publishing Ltd 01.05.2016
Témata:
Algorithms
Analysis
Categories and Subject Descriptors (according to ACM CCS)
Coding
Construction
Digitization and Image Capture
Exposure
I.4.1 [Image Processing and Computer Vision]
Image acquisition
Image processing systems
Image reconstruction
Imaging
Reconstruction
Sensors
Studies
ISSN:0167-7055, 1467-8659
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Current HDR acquisition techniques are based on either (i) fusing multibracketed, low dynamic range (LDR) images, (ii) modifying existing hardware and capturing different exposures simultaneously with multiple sensors, or (iii) reconstructing a single image with spatially‐varying pixel exposures. In this paper, we propose a novel algorithm to recover high‐quality HDRI images from a single, coded exposure. The proposed reconstruction method builds on recently‐introduced ideas of convolutional sparse coding (CSC); this paper demonstrates how to make CSC practical for HDR imaging. We demonstrate that the proposed algorithm achieves higher‐quality reconstructions than alternative methods, we evaluate optical coding schemes, analyze algorithmic parameters, and build a prototype coded HDR camera that demonstrates the utility of convolutional sparse HDRI coding with a custom hardware platform.
Bibliografie:ark:/67375/WNG-5V53S5KJ-H
Supporting Information
istex:1CD5C26A7332B038D843F85F99B82C13A2652817
ArticleID:CGF12819
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.12819