Perceptual Quality Assessment for Multi-Exposure Image Fusion

Abstract

Multi-exposure image fusion (MEF) is considered an effective quality enhancement technique widely adopted in consumer electronics, but little work has been dedicated to the perceptual quality assessment of multi-exposure fused images. In this paper, we first build an MEF database and carry out a subjective user study to evaluate the quality of images generated by different MEF algorithms. There are several useful findings. First, considerable agreement has been observed among human subjects on the quality of MEF images. Second, no single state-of-the-art MEF algorithm produces the best quality for all test images. Third, the existing objective quality models for general image fusion are very limited in predicting perceived quality of MEF images. Motivated by the lack of appropriate objective models, we propose a novel objective image quality assessment (IQA) algorithm for MEF images based on the principle of the structural similarity approach and a novel measure of patch structural consistency. Our experimental results on the subjective database show that the proposed model well correlates with subjective judgments and significantly outperforms the existing IQA models for general image fusion. Finally, we demonstrate the potential application of the proposed model by automatically tuning the parameters of MEF algorithms.

Spatially Variant Laplacian Pyramids for Multi-frame Exposure Fusion

“…Quantitative comparison results against the boosted Laplacian Pyramid proposed by Shen et al [6], gradient field exposure fusion proposed by Gu et al [8] and bilateral filter based multi-exposure compositing, proposed by Raman et al [11] are provided. The metric MEF-SSIM [10] proposed by Ma et al [10] is being used for comparison. This metric is chosen for the objective evaluation of the proposed algorithm since it provides a way to analyse the perceptual image quality without the need of any reference images.…”

“…The metric is based on the multi-scale SSIM principle [12] and measures the local structure preservation of the output image with respect to input images at fine scales and luminance consistency at coarser scales. For a more detailed discussion on the metric, the readers may refer to [10].…”

“…The algorithms are evaluated on the public dataset provided by [10]. The results are summarized in Table 1.…”

An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures

“…The quality of images produced by each method was evaluated in two objective metrics; TMQI [17] and MEF-SSIM [18]. TMQI measures the quality of a tone mapped image from an HDR image and it consists of structural fidelity and statistical naturalness.…”

“…We evaluate the effectiveness of the proposed method in terms of the quality of generated images by two simulations. In the simulations, the proposed method is compared with conventional MEF methods in terms of objective quality metrics: the tone mapped image quality index (TMQI) [17], MEF structural similarity (MEF-SSIM) [18], statistical naturalness, and discrete entropy. Experimental results show that the proposed method can produce high-quality images compared with conventional fusion methods for single-shot high dynamic range imaging with SVE.…”