Multiple-Exposure Image Fusion for HDR Image Synthesis Using Learned Analysis Transformations.

Ioannis Merianos,Nikolaos Mitianoudis

doi:10.3390/jimaging5030032

Abstract

Modern imaging applications have increased the demand for High-Definition Range (HDR) imaging. Nonetheless, HDR imaging is not easily available with low-cost imaging sensors, since their dynamic range is rather limited. A viable solution to HDR imaging via low-cost imaging sensors is the synthesis of multiple-exposure images. A low-cost sensor can capture the observed scene at multiple-exposure settings and an image-fusion algorithm can combine all these images to form an increased dynamic range image. In this work, two image-fusion methods are combined to tackle multiple-exposure fusion. The luminance channel is fused using the Mitianoudis and Stathaki (2008) method, while the color channels are combined using the method proposed by Mertens et al. (2007). The proposed fusion algorithm performs well without halo artifacts that exist in other state-of-the-art methods. This paper is an extension version of a conference, with more analysis on the derived method and more experimental results that confirm the validity of the method.

Highlights

The recent technological progress in imaging sensors development has triggered the introduction of image cameras with very high specifications
The proposed fusion algorithm performs well without halo artifacts that exist in other state-of-the-art methods
We propose a multiple-exposure fusion algorithm, where the luminance channels are fused via the independent component analysis (ICA)-based image-fusion approach of [4], while the chrominance channels are fused using the Mertens et al method [3]

Summary

Introduction

The recent technological progress in imaging sensors development has triggered the introduction of image cameras with very high specifications. The problem of capturing natural scenes, in the same quality as captured by the human visual system, is far from being solved with today’s technology. Imaging sensors in modern cameras feature maximum-to-minimum light intensity of approximately 28 –217. The maximum-to-minimum light intensity ratio is termed dynamic range. The logarithm of the dynamic range with base 2 is measured in stops. A commercial DSLR camera can capture scenes with 8–12 stops dynamic range. Professional movie cameras, such as the Red Monstro (https://www.red.com/dsmc2), can capture scenes with approximately

Methods

Results

Conclusion