Quality Assessment for Tone-Mapped HDR Images Using Multi-Scale and Multi-Layer Information

TL;DR

This paper introduces a no-reference quality assessment method for tone-mapped HDR images that leverages multi-scale and multi-layer features from a pre-trained deep neural network, outperforming existing methods.

Contribution

It presents a novel no-reference TMIQA approach using multi-scale, multi-layer features from deep CNNs, improving accuracy over prior techniques.

Findings

Outperforms existing no-reference TMIQA methods

Effective in handling complex distortions in tone-mapped images

Validated on the largest public TMIQA database

Abstract

Tone mapping operators and multi-exposure fusion methods allow us to enjoy the informative contents of high dynamic range (HDR) images with standard dynamic range devices, but also introduce distortions into HDR contents. Therefore methods are needed to evaluate tone-mapped image quality. Due to the complexity of possible distortions in a tone-mapped image, information from different scales and different levels should be considered when predicting tone-mapped image quality. So we propose a new no-reference method of tone-mapped image quality assessment based on multi-scale and multi-layer features that are extracted from a pre-trained deep convolutional neural network model. After being aggregated, the extracted features are mapped to quality predictions by regression. The proposed method is tested on the largest public database for TMIQA and compared to existing no-reference methods. The experimental results show that the proposed method achieves better performance.