Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Image Quality Assessment: Exploring Regional Heterogeneity via Response of Adaptive Multiple Quality Factors in Dictionary Space

Xuting Lan, Mingliang Zhou, Jielu Yan, Xuekai Wei, Yueting Huang, Zhaowei Shang, Huayan Pu

TL;DR

An adaptive multi-quality factor (AMqF) framework to represent image quality in a dictionary space, enabling the precise capture of quality features in non-uniformly distorted regions and significantly improving the accuracy of visual similarity measurement is proposed.

Abstract

Given that the factors influencing image quality vary significantly with scene, content, and distortion type, particularly in the context of regional heterogeneity, we propose an adaptive multi-quality factor (AMqF) framework to represent image quality in a dictionary space, enabling the precise capture of quality features in non-uniformly distorted regions. By designing an adapter, the framework can flexibly decompose quality factors (such as brightness, structure, contrast, etc.) that best align with human visual perception and quantify them into discrete visual words. These visual words respond to the constructed dictionary basis vector, and by obtaining the corresponding coordinate vectors, we can measure visual similarity. Our method offers two key contributions. First, an adaptive mechanism that extracts and decomposes quality factors according to human visual perception principles enhances their representation ability through reconstruction constraints. Second, the construction of a comprehensive and discriminative dictionary space and basis vector allows quality factors to respond effectively to the dictionary basis vector and capture non-uniform distortion patterns in images, significantly improving the accuracy of visual similarity measurement. The experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches in handling various types of distorted images. The source code is available at https://anonymous.4open.science/r/AMqF-44B2.

Image Quality Assessment: Exploring Regional Heterogeneity via Response of Adaptive Multiple Quality Factors in Dictionary Space

TL;DR

An adaptive multi-quality factor (AMqF) framework to represent image quality in a dictionary space, enabling the precise capture of quality features in non-uniformly distorted regions and significantly improving the accuracy of visual similarity measurement is proposed.

Abstract

Given that the factors influencing image quality vary significantly with scene, content, and distortion type, particularly in the context of regional heterogeneity, we propose an adaptive multi-quality factor (AMqF) framework to represent image quality in a dictionary space, enabling the precise capture of quality features in non-uniformly distorted regions. By designing an adapter, the framework can flexibly decompose quality factors (such as brightness, structure, contrast, etc.) that best align with human visual perception and quantify them into discrete visual words. These visual words respond to the constructed dictionary basis vector, and by obtaining the corresponding coordinate vectors, we can measure visual similarity. Our method offers two key contributions. First, an adaptive mechanism that extracts and decomposes quality factors according to human visual perception principles enhances their representation ability through reconstruction constraints. Second, the construction of a comprehensive and discriminative dictionary space and basis vector allows quality factors to respond effectively to the dictionary basis vector and capture non-uniform distortion patterns in images, significantly improving the accuracy of visual similarity measurement. The experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches in handling various types of distorted images. The source code is available at https://anonymous.4open.science/r/AMqF-44B2.

Paper Structure

This paper contains 16 sections, 8 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Image Quality Assessment
  4. Deep feature-based Image Quality Assessment
  5. Problem Formulation
  6. Methodology
  7. Framework
  8. Adaptive Multi-Quality Factors
  9. Response of Factors in Dictionary Space
  10. Connection to the HVS and existing methods
  11. Experiments
  12. Experimental setups
  13. Experimental Results
  14. Comparison with the State-of-the-Art Method
  15. Ablation Study and Analysis
  16. ...and 1 more sections

Figures (2)

  • Figure 1: Framework of our proposed method (AMqF).
  • Figure 2: Scatter plots of the prediction results for various FR-IQA methods on the KADID-10k kadid dataset, as well as scatter plots of our method (AMqF) on the LIVE, CSIQ and TID2013 datasets.