以人为中心的多曝光融合：基准与双层认知蒸馏框架
Human-Centric Multi-Exposure Fusion: Benchmark and Bi-level Cognition Distillation Framework
把EEG认知信号作为教师端的先验来监督低层视觉特征学习，再蒸馏到只用图像输入的轻量学生网络，为「用生理信号定义感知质量、但推理时不需要生理信号」提供了一套可复用的双层优化范式，可直接迁移到去噪、增强等其它低层任务的主观质量对齐。
原文依据 a bi-level coupled learning framework that leverages this cognitive information without requiring it during inference
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多曝光融合（MEF）旨在从不同曝光水平下采集的多幅输入图像生成单幅高质量图像。尽管已取得显著进展，现有方法大多依赖统计指标，而这些指标难以反映人类的感知偏好。脑电图（EEG）为人类认知提供了直接的生理观测窗口，但由于配对数据稀缺以及推理阶段缺乏生物信号，其在低层视觉中的应用仍然有限。我们通过两项关键贡献应对这些挑战。首先，我们提出 Cog-Expo，这是首个记录人类对多曝光刺激的认知反应的数据集，在神经科学与计算摄影之间建立了桥梁。其次，我们提出一种双层耦合学习框架，在推理阶段无需认知信息即可利用这些认知信息。一个心理整合 Transformer 作为教师，引入认知先验来引导视觉特征学习；同时训练一个轻量学生网络，仅使用图像输入来逼近这些线索。通过双层优化，教师学习到本质上可蒸馏的表征，使学生能够高效地模拟认知引导。大量实验证实，我们的方法取得了最优的融合性能，并且更贴近人类感知。
英文原文摘要 1365 字符
Multi-Exposure Fusion (MEF) seeks to generate a single high-quality image from multiple inputs captured at different exposure levels. Despite substantial progress, most existing approaches depend on statistical metrics that poorly reflect human perceptual preferences. Electroencephalography (EEG) provides a direct physiological window into human cognition, yet its use in low-level vision remains limited due to scarce paired data and the absence of bio-signals during inference. We address these challenges through two key contributions. First, we introduce Cog-Expo, the first dataset capturing human cognitive responses to multi-exposure stimuli, establishing a bridge between neuroscience and computational photography. Second, we propose a bi-level coupled learning framework that leverages this cognitive information without requiring it during inference. A Mental Integrated Transformer serves as the Teacher, incorporating cognitive priors to guide visual feature learning, while a lightweight Student is trained to approximate these cues using only image inputs. Through bi-level optimization, the Teacher learns inherently distillable representations, enabling the Student to emulate cognitive guidance efficiently. Extensive experiments confirm that our method achieves state-of-the-art fusion performance and aligns more closely with human perception.