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.

翻译：单图像超分辨率（SR）技术借助深度学习已取得显著进展，但大多数方法依赖于面向失真的损失函数或启发式感知先验，这往往导致保真度与视觉质量之间的权衡。为解决此问题，我们提出一种\textit{高效感知双向注意力网络（Efficient-PBAN）}，该网络显式地将超分辨率优化导向人类偏好的质量。与基于图像块的质量模型不同，Efficient-PBAN避免了大量的块采样，实现了高效的图像级感知。该框架在我们自建的超分辨率质量数据集上进行训练，该数据集涵盖了广泛的先进超分辨率方法及其对应的人类主观评分。通过该数据集，Efficient-PBAN学习以与主观判断高度相关的方式预测感知质量。习得的度量指标进一步作为可微分感知损失集成到超分辨率训练中，实现了重建与感知评估之间的闭环对齐。大量实验表明，我们的方法能够提供卓越的感知质量。代码公开于 https://github.com/Lighting-YXLI/Efficient-PBAN。