Perceptual Quality Optimization of Image Super-Resolution

2026-02-24

AI Summary

This work addresses the longstanding challenge in image super-resolution of simultaneously achieving high fidelity and strong perceptual quality aligned with human visual preferences. To this end, the authors propose the Efficient Perceptual Bidirectional Attention Network (Efficient-PBAN) and introduce, for the first time, an image-level super-resolution quality dataset annotated with human subjective scores. Their approach enables end-to-end perceptual quality modeling without patch-based sampling by integrating a differentiable perceptual prediction module directly into the super-resolution training pipeline, thereby establishing a closed-loop optimization between perceptual evaluation and image reconstruction. Experimental results demonstrate that the proposed method significantly enhances the subjective visual quality of generated images and outperforms existing state-of-the-art approaches across multiple benchmarks. The code has been made publicly available.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Semi-Supervised Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual quality. To address this issue, we propose an \textit{Efficient Perceptual Bi-directional Attention Network (Efficient-PBAN)} that explicitly optimizes SR towards human-preferred quality. Unlike patch-based quality models, Efficient-PBAN avoids extensive patch sampling and enables efficient image-level perception. The proposed framework is trained on our self-constructed SR quality dataset that covers a wide range of state-of-the-art SR methods with corresponding human opinion scores. Using this dataset, Efficient-PBAN learns to predict perceptual quality in a way that correlates strongly with subjective judgments. The learned metric is further integrated into SR training as a differentiable perceptual loss, enabling closed-loop alignment between reconstruction and perceptual assessment. Extensive experiments demonstrate that our approach delivers superior perceptual quality. Code is publicly available at https://github.com/Lighting-YXLI/Efficient-PBAN.

Problem

• image super-resolution
• perceptual quality
• fidelity-visual quality trade-off
• human opinion scores
• perceptual optimization

Innovation

• Perceptual Quality
• Image Super-Resolution
• Bi-directional Attention
• Differentiable Loss
• Human Preference