Convolutional sparse coding for high dynamic range imaging

Serrano, A. (Universidad de Zaragoza) ; Heide, F. ; Gutierrez, D. (Universidad de Zaragoza) ; Wetzstein, G. ; Masia, B. (Universidad de Zaragoza)

Resumen: 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.

Idioma: Inglés

DOI: 10.1111/cgf.12819

Año: 2016

Publicado en: COMPUTER GRAPHICS FORUM 35, 2 (2016), 153-163
ISSN: 0167-7055

Factor impacto JCR: 1.611 (2016)

Categ. JCR: COMPUTER SCIENCE, SOFTWARE ENGINEERING rank: 44 / 106 = 0.415 (2016) - Q2 - T2

Factor impacto SCIMAGO: 0.732 - Computer Networks and Communications (Q1) - Computer Graphics and Computer-Aided Design (Q1)

Financiación: info:eu-repo/grantAgreement/ES/MINECO/Lightslice

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Lenguajes y Sistemas Inf. (Dpto. Informát.Ingenie.Sistms.)