RawMetaDiff：利用元数据引导扩散从双曝光RAW中解锁极端黑暗
RawMetaDiff: Unlocking Extreme Darkness from Dual-Exposure RAW with Meta-Guided Diffusion
利用RAW元数据引导扩散模型进行跨曝光对齐和颜色校正，为极端低光照图像复原提供可复用的生成式框架，其元数据辅助的颜色迁移和跨注意力机制可迁移到其他多帧融合任务。
原文依据 we propose RawMetaDiff, a novel generative diffusion framework that restores a high-fidelity Raw image from a short-exposure input, conditioned on a potentially misaligned long-exposure reference under the guidance of Raw metadata.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论极端低光照RAW图像复原由于严重的噪声和细节丢失仍然具有挑战性。本文针对这一严重病态问题，挖掘了双曝光设置的潜力。现有方法受限于不可靠的跨曝光对齐，导致细节恢复退化与颜色保真度受损。为解决这些挑战，我们提出RawMetaDiff，一种新颖的生成式扩散框架，在RAW元数据的引导下，以可能未对齐的长曝光参考为条件，从短曝光输入中恢复高保真RAW图像。其核心是我们提出了两种互补机制：元数据辅助颜色迁移（MACT）通过沿通道维度对齐全局颜色统计量来强制颜色一致性，而元数据归一化跨注意力（MNCA）利用RAW元数据建立鲁棒的跨曝光空间对应关系并注入暗部细节。为支持鲁棒的扩散训练，我们首先收集了一个1K真实世界双曝光RAW数据集，命名为DERaw，然后设计了一个逼真的退化模型来合成接近真实世界条件的数据。在合成和真实世界数据集上的大量实验表明，RawMetaDiff显著优于现有方法，从生成角度为极端低光照RAW图像复原证明了一种有效的新解决方案。
英文原文摘要 1425 字符
Extreme low-light Raw image restoration remains challenging due to overwhelming noise and severe detail loss.In this paper, we exploit the potential of the dual-exposure setting for this severely ill-posed problem.Existing methods suffer from unreliable cross-exposure alignment, resulting in degraded detail recovery and compromised color fidelity. To address these challenges, we propose RawMetaDiff, a novel generative diffusion framework that restores a high-fidelity Raw image from a short-exposure input, conditioned on a potentially misaligned long-exposure reference under the guidance of Raw metadata.At its core, we propsed two complementary mechanisms: the Meta-Assistant Color Transfer (MACT) enforces color consistency by aligning global color statistics along the channel dimension,while the Meta-Normed Cross Attention (MNCA) leverages Raw metadata to establish robust cross-exposure spatial correspondences and inject shadow details.To support robust diffusion training, we first collect a 1K real-world, dual-exposure Raw dataset, namely DERaw, and then design a realistic degradation model to synthesize data that closely approximates real-world conditions.Extensive experiments on both synthetic and real-world datasets demonstrate that RawMetaDiff significantly outperforms existing methods, justifying an effective new solution for extreme low-light Raw image restoration from the generative perspective.