Deep Multi-Scale Features Learning for Distorted Image Quality Assessment

TL;DR

This paper introduces a deep neural network that leverages hierarchical multi-scale features inspired by the human visual system to improve distorted image quality assessment accuracy.

Contribution

It proposes a novel pyramid features learning approach with spatial pyramid pooling and feature pyramids for enhanced IQA performance.

Findings

Outperforms existing IQA models on four benchmark databases.

Effectively utilizes multi-scale features for better perceptual quality prediction.

Demonstrates robustness across various types of image distortions.

Abstract

Image quality assessment (IQA) aims to estimate human perception based image visual quality. Although existing deep neural networks (DNNs) have shown significant effectiveness for tackling the IQA problem, it still needs to improve the DNN-based quality assessment models by exploiting efficient multi-scale features. In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction. Our model is based on both residual maps and distorted images in luminance domain, where the proposed network contains spatial pyramid pooling and feature pyramid from the network structure. Our proposed network is optimized in a deep end-to-end supervision manner. To validate the effectiveness of the proposed method, extensive experiments are conducted on four widely-used image quality assessment databases, demonstrating the superiority of our algorithm.