论文标题
过度暴露掩模融合：可推广的反向ISP多步进
Overexposure Mask Fusion: Generalizable Reverse ISP Multi-Step Refinement
论文作者
论文摘要
随着深度学习方法的出现，将ISP替换为将传感器原始读数转换为RGB图像的出现，许多方法将固化为现实生活中的应用。同样有效的是颠倒此过程的任务，该过程将在加强原始域中执行的计算摄影任务时具有应用程序，从而解决了缺乏可用的原始数据，同时从直接在传感器读取上执行任务的好处。本文提出的方法是针对原始重建任务的最先进的解决方案，而整合过度曝光掩码的多步进过程则是三种新颖的：从RGB到拜耳，从RGB到ExoSaiced的原始训练，允许使用感知损失功能；从头到尾，多步骤过程大大提高了基线U-NET的性能。该管道是一个可普遍的改进过程，可以增强支持端到端学习的其他高性能方法。
With the advent of deep learning methods replacing the ISP in transforming sensor RAW readings into RGB images, numerous methodologies solidified into real-life applications. Equally potent is the task of inverting this process which will have applications in enhancing computational photography tasks that are conducted in the RAW domain, addressing lack of available RAW data while reaping from the benefits of performing tasks directly on sensor readings. This paper's proposed methodology is a state-of-the-art solution to the task of RAW reconstruction, and the multi-step refinement process integrating an overexposure mask is novel in three ways: instead of from RGB to bayer, the pipeline trains from RGB to demosaiced RAW allowing use of perceptual loss functions; the multi-step processes has greatly enhanced the performance of the baseline U-Net from start to end; the pipeline is a generalizable process of refinement that can enhance other high performance methodologies that support end-to-end learning.
