Convolutional Sparse Coding for High Dynamic Range Imaging

dc.contributor.authorSerrano, Anaen_US
dc.contributor.authorHeide, Felixen_US
dc.contributor.authorGutierrez, Diegoen_US
dc.contributor.authorWetzstein, Gordonen_US
dc.contributor.authorMasia, Belenen_US
dc.contributor.editorJoaquim Jorge and Ming Linen_US
dc.description.abstractCurrent 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.en_US
dc.description.sectionheadersHDR Imagingen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.4.1 [Image Processing and Computer Vision]en_US
dc.subjectDigitization and Image Captureen_US
dc.titleConvolutional Sparse Coding for High Dynamic Range Imagingen_US