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 this https URL.
Abstract (translated)
单图像超分辨率（SR）通过深度学习取得了显著进展，但大多数方法依赖于针对失真优化的损失函数或基于直觉的人类感知先验，这往往会导致保真度和视觉质量之间的权衡。为了解决这一问题，我们提出了一种名为**Efficient Perceptual Bi-directional Attention Network (Efficient-PBAN)**的方法，该方法能够明确地优化超分辨率图像以符合人类的偏好质量标准。与基于补丁的质量模型不同，Efficient-PBAN避免了广泛的补丁采样，并且能够在图像级别实现高效感知。 我们构建了一个自有的SR质量数据集来训练所提出的框架，该数据集涵盖了多种最先进的SR方法及其对应的人类主观评分，从而使得Efficient-PBAN能够学习预测与主观评价紧密相关的感知质量。此外，我们还把学到的度量标准集成到SR模型训练中，作为可微分的感知损失函数，实现了重建和感知评估之间的闭环对齐。 通过广泛的实验验证，我们的方法在感知质量方面表现出色。代码可在以下链接公开获取：[提供的URL]（请将方括号内的文本替换为实际链接）。
URL
https://arxiv.org/abs/2602.21482
