发表机构
Southern University of Science and Technology; Pengcheng Laboratory（南方科技大学; 鹏城实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低光照图像增强无参考PSNR预测的空白，提出轻量级网络BlindPSNR，融合增强图像与低光照输入并通过异方差回归估计PSNR，大幅提升参数选择准确率且可泛化至未见数据集。
AI 中文摘要
低光照图像增强（LLIE）方法包含可调参数，这些参数通常是固定的，跨场景应用时往往会导致性能下降。然而手动选择最佳配置既耗时又不总是可行。峰值信噪比（PSNR）是用于自动参数选择的天然保真度准则，但它需要通常不可用的真实参考。据我们所知，尚无基于学习的方法解决低光照图像增强的无参考PSNR预测问题；天然替代方案无参考图像质量评估（NR-IQA）针对感知质量而非信号保真度，我们测试的7个基线在我们的基准上均达到0%的top-1选择准确率。利用配对训练数据，真实PSNR可解析计算，无需单独的教师网络即可提供精确监督。基于此，我们提出BlindPSNR，一种轻量级无参考网络，它通过窗口交叉注意力融合增强图像与退化的低光照输入，并通过异方差回归估计PSNR。标量回归基线的top-1准确率为54.4%，而BlindPSNR将其提升至89.5%，遗憾值从1.62 dB降至0.026 dB，且能泛化到未见数据集（SRCC=0.61-0.67）。
英文摘要
Low-light image enhancement (LLIE) methods involve tunable parameters that are typically fixed, often leading to performance degradation when applied across scenes. Manually selecting the best configuration, however, can be time-consuming and not always practical. Peak signal-to-noise ratio (PSNR) is the natural fidelity criterion for automating parameter selection, yet it requires a ground-truth reference that is typically unavailable. To our knowledge, no learning-based method addresses no-reference PSNR prediction for low-light image enhancement; the natural surrogate, no-reference image quality assessment (NR-IQA), targets perceptual quality rather than signal fidelity, and all seven baselines we test achieve 0% top-1 selection accuracy on our benchmark. With paired training data, the ground-truth PSNR is analytically computable, providing exact supervision without a separate teacher network. Building on this, we propose BlindPSNR, a lightweight no-reference network that fuses the enhanced image with the degraded low-light input via windowed cross-attention and estimates PSNR through heteroscedastic regression. While a scalar-regression baseline achieves top-1 accuracy of 54.4%, BlindPSNR raises this to 89.5% with regret dropping from 1.62 dB to 0.026 dB, and generalizes to unseen datasets (SRCC = 0.61-0.67).
