Quality assessment for multi-exposure fusion light field images with dynamic region segmentation

Abstract

The luminance dynamic range of real scenes can reach up to nine orders, whereas the existing light field camera captures light field images (LFIs) with a limited luminance dynamic range of about two orders. Although LFIs can be enhanced using multi-exposure fusion (MEF) technologies, this process introduces various distortions that affect human visual perception. Therefore, it is crucial to develop an effective quality assessment tool for multi-exposure fusion light field images (MEF-LFIs). Starting from the complex distortion characteristics generated by MEF with dynamic scenes, this paper proposes an MEF-LFI quality metric with dynamic region segmentation. The proposed metric consists of three main modules. The first module focuses on spatial feature extraction and incorporates a dynamic region segmentation scheme to address artifacts in MEF-LFIs. The second module utilizes Shearlet transform for spectrum feature extraction to characterize detail loss. Additionally, the third module addresses distortion in the angular domain of MEF-LFIs through angular feature extraction using epipolar plane images and tensor decomposition. Finally, the quality of the MEF-LFIs is evaluated by integrating spatial features, spectrum features and angular features into feature vectors which are then inputted into a regression model. The experimental results show that the proposed metric is superior to the representative quality metrics and has better consistency with the human visual perception.