Blind High Dynamic Range Quality estimation by disentangling perceptual and noise features in images

TL;DR

This paper introduces a novel CNN-based no-reference HDR image quality assessment model that disentangles noise and perceptual features, achieving state-of-the-art performance comparable to full-reference methods.

Contribution

The paper presents a new HDR NR-IQA model that separately estimates noise and perceptual effects, trained on real-world datasets, enhancing accuracy without reference images.

Findings

Achieves state-of-the-art HDR NR-IQA performance

Performs comparably to full-reference IQA algorithms

Effectively disentangles noise and perceptual features

Abstract

Assessing the visual quality of High Dynamic Range (HDR) images is an unexplored and an interesting research topic that has become relevant with the current boom in HDR technology. We propose a new convolutional neural network based model for No reference image quality assessment(NR-IQA) on HDR data. This model predicts the amount and location of noise, perceptual influence of image pixels on the noise, and the perceived quality, of a distorted image without any reference image. The proposed model extracts numerical values corresponding to the noise present in any given distorted image, and the perceptual effects exhibited by a human eye when presented with the same. These two measures are extracted separately yet sequentially and combined in a mixing function to compute the quality of the distorted image perceived by a human eye. Our training process derives the the component that computes perceptual effects from a real world image quality dataset, rather than using results of psycovisual experiments. With the proposed model, we demonstrate state of the art performance for HDR NR-IQA and our results show performance similar to HDR Full Reference Image Quality Assessment algorithms (FR-IQA).