Convolutional Sparse Coding for High Dynamic Range Imaging
This addresses the challenge of HDR acquisition for imaging applications, offering a more efficient single-exposure approach compared to existing multi-exposure or hardware-intensive methods.
The paper tackles the problem of high dynamic range (HDR) imaging by proposing a novel algorithm to recover high-quality HDR images from a single coded exposure, achieving higher-quality reconstructions than alternative methods.
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.