论文标题
低光原始denoising的可学习性增强：配对的真实数据符合噪声建模
Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling
论文作者
论文摘要
在计算摄影中，低光原始denoising是一项重要且有价值的任务，在计算摄影中，基于成对的真实数据训练的基于学习的方法是主流。但是，有限的数据量和复杂的噪声分布构成了配对真实数据的可学习性瓶颈，这限制了基于学习的方法的降解性能。为了解决这个问题，我们提出了一种可学习性增强策略，以根据噪声建模改革成对的真实数据。我们的策略包括两种有效的技术：射击噪声增强（SNA）和深色阴影校正（DSC）。通过噪声模型解耦，SNA通过增加数据量和DSC来提高数据映射的精度，并通过降低噪声复杂性来降低数据映射的复杂性。公共数据集和真实成像方案的广泛结果共同证明了我们方法的最新性能。我们的代码可在以下网址提供：https：//github.com/megvii-research/pmn。
Low-light raw denoising is an important and valuable task in computational photography where learning-based methods trained with paired real data are mainstream. However, the limited data volume and complicated noise distribution have constituted a learnability bottleneck for paired real data, which limits the denoising performance of learning-based methods. To address this issue, we present a learnability enhancement strategy to reform paired real data according to noise modeling. Our strategy consists of two efficient techniques: shot noise augmentation (SNA) and dark shading correction (DSC). Through noise model decoupling, SNA improves the precision of data mapping by increasing the data volume and DSC reduces the complexity of data mapping by reducing the noise complexity. Extensive results on the public datasets and real imaging scenarios collectively demonstrate the state-of-the-art performance of our method. Our code is available at: https://github.com/megvii-research/PMN.
