A Survey on Image Quality Assessment: Insights, Analysis, and Future Outlook

2025-02-12

AI Summary

Image quality assessment (IQA) faces core challenges including poor scene adaptability, limited interpretability, and difficulties in engineering deployment. This paper presents a systematic survey of recent IQA advances, categorizing methods—classical metrics (e.g., PSNR, SSIM), machine learning approaches (e.g., SVM, RF), and deep models (e.g., CNN, ViT)—by application scenario. Crucially, it is the first to integrate distortion-specific requirements with practical constraints—including utility, interpretability, and implementation simplicity—into a unified methodological framework. We propose an application-oriented IQA evaluation taxonomy and construct a comprehensive landscape spanning general-purpose and domain-specific methods. Key technical bottlenecks are explicitly identified, and empirically grounded future research directions are provided. The work establishes a benchmark reference for the IQA community, balancing theoretical rigor with actionable engineering guidance.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Other Foundations and Applications

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Image quality assessment (IQA) represents a pivotal challenge in image-focused technologies, significantly influencing the advancement trajectory of image processing and computer vision. Recently, IQA has witnessed a notable surge in innovative research efforts, driven by the emergence of novel architectural paradigms and sophisticated computational techniques. This survey delivers an extensive analysis of contemporary IQA methodologies, organized according to their application scenarios, serving as a beneficial reference for both beginners and experienced researchers. We analyze the advantages and limitations of current approaches and suggest potential future research pathways. The survey encompasses both general and specific IQA methodologies, including conventional statistical measures, machine learning techniques, and cutting-edge deep learning models such as convolutional neural networks (CNNs) and Transformer models. The analysis within this survey highlights the necessity for distortion-specific IQA methods tailored to various application scenarios, emphasizing the significance of practicality, interpretability, and ease of implementation in future developments.

Problem

• Analyzes contemporary image quality assessment methods
• Explores distortion-specific IQA for various applications
• Proposes future research in practicality and interpretability

Innovation

• Deep learning CNNs
• Transformer models
• Distortion-specific IQA methods