AI 中文总结
提出PreSPA部分参考图像质量评估框架，通过结构感知和纹理敏感指标评估图像质量，将感知质量分解为两个互补指标，经仿射融合产生最终分数，在多基准测试中表现出色，媲美或超无参考方法，有时与全参考模型精度相当。
AI 中文摘要
我们提出了PreSPA（部分参考结构预测方法），这是一个部分参考图像质量评估框架，将感知质量分解为两个互补指标。一个结构感知指标以无参考方式运行，通过对失真梯度场的埃尔米特 - 高斯预测及其曲率的角方差来捕获结构退化。一个纹理敏感指标通过标量先验μ估计局部噪声，μ从参考和失真复梯度图在强边缘区域的能量差获得，并在弱结构区域累积，反映退化边缘到周围纹理的感知泄漏。关键的是，μ是从参考中提取的唯一信息，每个图像对仅计算一次，将参考足迹减少到信息理论最小值。最终分数由仅具有三个可解释参数的仿射融合产生，使该方法紧凑、透明且计算高效，观看距离嵌入到算子尺度中且无需特定数据集校准。在六个标准基准上的广泛评估表明，PreSPA始终与领先的无参考方法相媲美或超过它们，在某些情况下与全参考模型的准确性相当。
英文摘要
We propose PreSPA (Partial-Reference Structural Prediction Approach), a Partial-Reference Image Quality Assessment framework that decomposes perceptual quality into two complementary indices. A structure-aware index, operating in a No-Reference manner, captures structural degradation through Hermite-Gauss prediction of the distorted gradient field and the angular variance of its curvature. A texture-sensitive index estimates local noise through a scalar prior $μ$, obtained from energy differences between reference and distorted complex gradient maps on strong-edge regions and accumulated over weakly-structured ones, reflecting the perceptual leakage of degraded edges into surrounding textures. Crucially, $μ$ is the only information extracted from the reference and is computed once per image pair, reducing the reference footprint to a single scalar value. The final score is produced by an affine fusion with only three interpretable parameters, making the method compact, transparent, and computationally efficient, with the viewing distance embedded into the operator scale and no dataset-specific calibration. Extensive evaluations on six standard benchmarks show that PreSPA consistently rivals or exceeds leading No-Reference approaches, while in several cases matching the accuracy of Full-Reference models.
