面向真实智能手机超分辨率的RAW域退化模型
RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution
用标定得到的设备特定模糊与噪声参数替代通用先验，把公开渲染图像 unprocess 到各手机 RAW 域构造成对训练数据，可直接迁移到其他 RAW 域复原任务（去噪、去模糊、低光增强）的合成数据构造环节。
原文依据 we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论智能手机上的数码变焦依赖在 RAW 传感器图像上运行的基于学习的超分辨率（SR）模型，但由于缺乏真值图像，获取传感器特定的训练数据十分困难。通过“unprocessing”管线生成合成数据提供了一种可能的解决方案，即模拟将高分辨率（HR）图像变换为其低分辨率（LR）对应图像的退化过程。然而，这些管线由于退化建模不完整或不真实，可能引入域差距。本文表明，有原则且精心设计的退化建模能够提升真实条件下的 SR 性能。我们不依赖相机模糊与噪声的通用先验，而是通过标定对设备特定的退化进行建模，并将公开可用的渲染图像 unprocess 到不同智能手机的 RAW 域。利用这些图像对，我们训练了一个在马赛克 RAW 图像上运行的单图像 SR 模型，并在来自留出设备的真实数据上对其进行评估。实验表明，准确的退化建模带来了明显改进，我们的 SR 模型优于在大量任意选择的退化上训练的基线模型。
英文原文摘要 1223 字符
Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data generation via "unprocessing" pipelines offers a potential solution by simulating the degradations that transform high-resolution (HR) images into their low-resolution (LR) counterparts. However, these pipelines can introduce domain gaps due to incomplete or unrealistic degradation modeling. In this paper, we demonstrate that principled and carefully designed degradation modeling can enhance SR performance in real-world conditions. Instead of relying on generic priors for camera blur and noise, we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones. Using these image pairs, we train a single-image SR model that operates on mosaicked RAW images and evaluate it on real data from a held-out device. Our experiments show that accurate degradation modeling leads to noticeable improvements, with our SR model outperforming baselines trained on large pools of arbitrarily chosen degradations.