编辑感知的 RAW 重建
Edit-aware RAW reconstruction
把可微 ISP 当作损失函数的渲染算子，在 sRGB 空间监督 RAW 重建，使恢复的 RAW 对渲染风格和后期编辑更鲁棒；这一「在显示域而非传感器域算损失」的思路可直接迁移到去噪、超分、低光照增强等需要下游 ISP 配合的底层视觉任务。
原文依据 We introduce a plug-and-play, edit-aware loss function that can be integrated into any existing RAW reconstruction framework
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论用户常在拍摄后对相机图像进行编辑，以获得偏好的照片冲印风格。虽然在 RAW 域编辑能带来更高的精度与灵活性，但由于 RAW 图像很少被保存，大多数编辑实际上是在相机的显示参考输出（例如 8 位 sRGB JPEG）上进行的。现有的 RAW 重建方法能够从 sRGB 图像恢复 RAW 数据，但这些方法通常针对逐像素的 RAW 重建保真度进行优化，在多样的渲染风格与编辑操作下往往性能下降。我们提出一种即插即用、编辑感知的损失函数，可集成到任何现有的 RAW 重建框架中，使恢复出的 RAW 对不同的渲染风格与编辑更加鲁棒。我们的损失构造引入了一个模块化、可微的图像信号处理器（ISP），用于模拟带有可调参数的真实照片冲印流程。训练时，每个 ISP 模块的参数从精心设计的分布中随机采样，这些分布刻画了真实相机处理中的实际变化。随后，损失在此可微 ISP 渲染出的真值 RAW 与重建 RAW 之间于 sRGB 空间计算。引入该损失后，在各种编辑条件下 sRGB 重建质量最高提升 1.5–2 dB 峰值信噪比。此外，当应用于元数据辅助的 RAW 重建方法时，我们的方法能够针对目标编辑进行微调，带来进一步的增益。由于照片编辑是消费级成像中进行 RAW 重建的主要动机，我们这一简单而有效的损失函数为提升现有方法的编辑保真度与渲染灵活性提供了一种通用机制。
英文原文摘要 1705 字符
Users frequently edit camera images post-capture to achieve their preferred photofinishing style. While editing in the RAW domain provides greater accuracy and flexibility, most edits are performed on the camera's display-referred output (e.g., 8-bit sRGB JPEG) since RAW images are rarely stored. Existing RAW reconstruction methods can recover RAW data from sRGB images, but these approaches are typically optimized for pixel-wise RAW reconstruction fidelity and tend to degrade under diverse rendering styles and editing operations. We introduce a plug-and-play, edit-aware loss function that can be integrated into any existing RAW reconstruction framework to make the recovered RAWs more robust to different rendering styles and edits. Our loss formulation incorporates a modular, differentiable image signal processor (ISP) that simulates realistic photofinishing pipelines with tunable parameters. During training, parameters for each ISP module are randomly sampled from carefully designed distributions that model practical variations in real camera processing. The loss is then computed in sRGB space between ground-truth and reconstructed RAWs rendered through this differentiable ISP. Incorporating our loss improves sRGB reconstruction quality by up to 1.5-2 dB PSNR across various editing conditions. Moreover, when applied to metadata-assisted RAW reconstruction methods, our approach enables fine-tuning for target edits, yielding further gains. Since photographic editing is the primary motivation for RAW reconstruction in consumer imaging, our simple yet effective loss function provides a general mechanism for enhancing edit fidelity and rendering flexibility across existing methods.