Noise synthesis is a challenging low-level vision task aiming to generate realistic noise given a clean image along with the camera settings. To this end, we propose an effective generative model which utilizes clean features as guidance followed by noise injections into the network. Specifically, our generator follows a UNet-like structure with skip connections but without downsampling and upsampling layers. Firstly, we extract deep features from a clean image as the guidance and concatenate a Gaussian noise map to the transition point between the encoder and decoder as the noise source. Secondly, we propose noise synthesis blocks in the decoder in each of which we inject Gaussian noise to model the noise characteristics. Thirdly, we propose to utilize an additional Style Loss and demonstrate that this allows better noise characteristics supervision in the generator. Through a number of new experiments, we evaluate the temporal variance and the spatial correlation of the generated noise which we hope can provide meaningful insights for future works. Finally, we show that our proposed approach outperforms existing methods for synthesizing camera noise.

翻译：噪声合成是一项具有挑战性的底层视觉任务，旨在根据给定的干净图像及相机设置生成逼真的噪声。为此，我们提出了一种高效的生成模型，该模型利用干净特征作为引导，并在网络中进行噪声注入。具体而言，我们的生成器采用类似UNet的结构，带有跳跃连接，但省略了下采样和上采样层。首先，我们从干净图像中提取深层特征作为引导，并在编码器与解码器的过渡点拼接高斯噪声图作为噪声源。其次，我们在解码器中提出噪声合成块，每个块中注入高斯噪声以建模噪声特性。第三，我们提出利用额外的风格损失，并证明该损失能在生成器中提供更好的噪声特性监督。通过一系列新实验，我们评估了生成噪声的时间方差和空间相关性，希望为未来研究提供有意义的见解。最后，我们证明所提出的方法在合成相机噪声方面优于现有方法。