UCMNet：面向屏下摄像头图像复原的不确定性感知上下文记忆网络
UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration
用不确定性图作为空间先验来引导记忆库检索区域自适应上下文，这一「不确定性驱动 + 记忆检索」范式可迁移到其他空间非均匀退化复原任务（如散焦去模糊、镜头污渍、混合退化去噪），且以更少参数达到最优，对轻量化复原网络设计有直接参考价值。
原文依据 The estimated uncertainty maps, learned through an uncertainty-driven loss, quantify spatial uncertainty induced by diffraction and scattering, and guide the Memory Bank to retrieve region-adaptive context from the Context Bank.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论屏下摄像头（UDC）通过将成像传感器置于显示屏下方，实现了全面屏设计。然而，光线穿过各层显示材料时发生的衍射与散射会导致空间变化且复杂的退化，显著削弱高频细节。当前基于点扩散函数（PSF）的物理建模技术与频率分离网络能够有效重建低频结构并保持整体色彩一致性，但在处理复杂、空间变化的退化时，仍难以恢复精细细节。为解决该问题，我们提出一种轻量级的不确定性感知上下文记忆网络（UCMNet），用于 UDC 图像复原。与以往采用统一复原方式的方法不同，UCMNet 执行不确定性感知的自适应处理，以恢复退化程度各异区域中的高频细节。所估计的不确定性图通过不确定性驱动损失学习得到，可量化由衍射与散射引起的空间不确定性，并引导记忆库从上下文库中检索区域自适应的上下文。该过程能够有效建模 UDC 成像固有的非均匀退化特性。以该不确定性作为先验，UCMNet 在多个基准上取得最优性能，且参数量较此前模型减少 30%。项目主页：https://kdhrick2222.github.io/projects/UCMNet。
英文原文摘要 1470 字符
Under-display cameras (UDCs) allow for full-screen designs by positioning the imaging sensor underneath the display. Nonetheless, light diffraction and scattering through the various display layers result in spatially varying and complex degradations, which significantly reduce high-frequency details. Current PSF-based physical modeling techniques and frequency-separation networks are effective at reconstructing low-frequency structures and maintaining overall color consistency. However, they still face challenges in recovering fine details when dealing with complex, spatially varying degradation. To solve this problem, we propose a lightweight Uncertainty-aware Context-Memory Network (UCMNet), for UDC image restoration. Unlike previous methods that apply uniform restoration, UCMNet performs uncertainty-aware adaptive processing to restore high-frequency details in regions with varying degradations. The estimated uncertainty maps, learned through an uncertainty-driven loss, quantify spatial uncertainty induced by diffraction and scattering, and guide the Memory Bank to retrieve region-adaptive context from the Context Bank. This process enables effective modeling of the non-uniform degradation characteristics inherent to UDC imaging. Leveraging this uncertainty as a prior, UCMNet achieves state-of-the-art performance on multiple benchmarks with 30% fewer parameters than previous models. Project page: https://kdhrick2222.github.io/projects/UCMNet.