Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Perceptual Quality Optimization of Image Super-Resolution

Wei Zhou, Yixiao Li, Hadi Amirpour, Xiaoshuai Hao, Jiang Liu, Peng Wang, Hantao Liu

TL;DR

This work proposes an Efficient Perceptual Bi-directional Attention Network (Efficient-PBAN), a model that explicitly optimizes SR towards human-preferred quality and avoids extensive patch sampling and enables efficient image-level perception.

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.

Perceptual Quality Optimization of Image Super-Resolution

TL;DR

This work proposes an Efficient Perceptual Bi-directional Attention Network (Efficient-PBAN), a model that explicitly optimizes SR towards human-preferred quality and avoids extensive patch sampling and enables efficient image-level perception.

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.
Paper Structure (9 sections, 8 equations, 2 figures, 2 tables)

This paper contains 9 sections, 8 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Proposed Method
  3. The proposed Efficient-PBAN
  4. Perceptual Optimization
  5. Experimental Results and Analysis
  6. Databases
  7. Experimental Setup
  8. Experimental Results
  9. Conclusion

Figures (2)

  • Figure 1: Overall framework of the proposed method. Left: SR optimization pipeline driven by Efficient-PBAN. Right: Efficient-PBAN structure with two-stage training, where the “ice" and “fire" icons denote frozen and trainable parameters, respectively. And the details of PBA$^{+}$ block are described in Section \ref{['section21']}. $\mathcal{L}_{D}$ and $\mathcal{L}_{P}$ refer to the distortion-oriented and perceptual loss, respectively.
  • Figure 2: Visualizations of the original SR images and the corresponding optimization results, where the regions highlighted by red boxes are enlarged for clearer illustration.