结合下采样不变性损失与条件盲点网络的自监督图像去噪
Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network
AI总结：
提出一种结合下采样不变性损失与条件盲点网络（C-BSN）的自监督图像去噪框架，通过控制网络盲目性并利用随机子采样器去除空间噪声相关性，在真实数据集上达到最先进性能。
摘要：
目前已经有许多使用深度神经网络的图像去噪器，它们以巨大优势超越了传统的基于模型的方法。最近，自监督方法引起了广泛关注，因为构建用于监督训练的大型真实噪声数据集是一项巨大的负担。最具代表性的自监督去噪器基于盲点网络，这种网络排除了感受野的中心像素。然而，排除任何输入像素都意味着放弃部分信息，尤其是当对应输出位置的输入像素被排除时。此外，尽管标准盲点网络能够成功去除独立分布的合成噪声，但由于噪声的像素级相关性，它无法有效降低真实的相机噪声。因此，为了实现更实用的去噪器，我们提出了一种能够去除真实噪声的新型自监督训练框架。为此，我们推导了监督损失的理论上界，其中网络由下采样的盲输出引导。同时，我们设计了条件盲点网络（C-BSN），它可以选择性地控制网络的盲目性以使用中心像素信息。此外，我们利用随机子采样器在空间上对噪声进行去相关，使得C-BSN免受基于下采样的方法中常见的视觉伪影影响。大量实验表明，所提出的C-BSN作为自监督去噪器在真实世界数据集上达到了最先进的性能，并在无需任何后处理或细化的情况下展现出令人满意的定性结果。
英文摘要：
There have been many image denoisers using deep neural networks, which outperform conventional model-based methods by large margins. Recently, self-supervised methods have attracted attention because constructing a large real noise dataset for supervised training is an enormous burden. The most representative self-supervised denoisers are based on blind-spot networks, which exclude the receptive field's center pixel. However, excluding any input pixel is abandoning some information, especially when the input pixel at the corresponding output position is excluded. In addition, a standard blind-spot network fails to reduce real camera noise due to the pixel-wise correlation of noise, though it successfully removes independently distributed synthetic noise. Hence, to realize a more practical denoiser, we propose a novel self-supervised training framework that can remove real noise. For this, we derive the theoretic upper bound of a supervised loss where the network is guided by the downsampled blinded output. Also, we design a conditional blind-spot network (C-BSN), which selectively controls the blindness of the network to use the center pixel information. Furthermore, we exploit a random subsampler to decorrelate noise spatially, making the C-BSN free of visual artifacts that were often seen in downsample-based methods. Extensive experiments show that the proposed C-BSN achieves state-of-the-art performance on real-world datasets as a self-supervised denoiser and shows qualitatively pleasing results without any post-processing or refinement.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
