MERIT：多域高效 RAW 图像翻译
MERIT: Multi-domain Efficient RAW Image Translation
把跨相机 RAW 域差异当作图像翻译问题，用单一模型覆盖任意源-目标相机对，并提出传感器感知的噪声建模损失对齐信号相关噪声统计；对做 RAW 域泛化、低层复原或多相机数据统一预处理的视觉研究者，这是一个可直接复用的噪声对齐思路和统一翻译框架。
原文依据 a sensor-aware noise modeling loss that explicitly aligns the signal-dependent noise statistics of the generated images with those of the target domain
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论不同相机传感器拍摄的 RAW 图像由于光谱响应、噪声特性和色调行为的差异而呈现出显著的域偏移，这使其难以直接用于下游计算机视觉任务。已有方法通过为每个源-目标相机对训练专用的 RAW 到 RAW 翻译器来解决该问题，但这类方法无法扩展到涉及多种商用相机的真实场景。本文提出 MERIT，这是首个面向多域 RAW 图像翻译的统一框架，利用单一模型在任意相机域之间执行翻译。为应对域特有的噪声差异，我们提出传感器感知的噪声建模损失，显式地将生成图像中依赖信号的噪声统计量与目标域的噪声统计量对齐。为便于标准化评测，我们提出 MDRAW，这是首个专为多域 RAW 图像翻译设计的数据集，包含来自五种不同相机传感器、覆盖广泛场景的配对与非配对 RAW 拍摄数据。大量实验表明，MERIT 在质量（+5.56 dB）与可扩展性（训练迭代次数减少 80%）两方面均优于已有模型。
英文原文摘要 1240 字符
RAW images captured by different camera sensors exhibit substantial domain shifts due to varying spectral responses, noise characteristics, and tone behaviors, complicating their direct use in downstream computer vision tasks. Prior methods address this problem by training domain-specific RAW-to-RAW translators for each source-target pair, but such approaches do not scale to real-world scenarios involving multiple types of commercial cameras. In this work, we introduce MERIT, the first unified framework for multi-domain RAW image translation, which leverages a single model to perform translations across arbitrary camera domains. To address domain-specific noise discrepancies, we propose a sensor-aware noise modeling loss that explicitly aligns the signal-dependent noise statistics of the generated images with those of the target domain. To facilitate standardized evaluation, we introduce MDRAW, the first dataset tailored for multi-domain RAW image translation, comprising both paired and unpaired RAW captures from five diverse camera sensors across a wide range of scenes. Extensive experiments demonstrate that MERIT outperforms prior models in both quality (+5.56 dB) and scalability (80% reduction in training iterations).