Back to Search Start Over

Convolutional Sparse Coding for High Dynamic Range Imaging

Authors :
Serrano, Ana
Heide, Felix
Gutierrez, Diego
Wetzstein, Gordon
Masia, Belen
Source :
Computer Graphics Forum 35, 2, Pages 153-163 (May 2016)
Publication Year :
2018

Abstract

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.

Details

Database :
arXiv
Journal :
Computer Graphics Forum 35, 2, Pages 153-163 (May 2016)
Publication Type :
Report
Accession number :
edsarx.1806.04942
Document Type :
Working Paper
Full Text :
https://doi.org/10.1111/cgf.12819