论文标题
noings2same：优化用于图像denoising的自我监督的绑定
Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising
论文作者
论文摘要
在各种嘈杂的图像中学习具有单独的嘈杂图像的Denoing模型的自我监督框架表现出强大的能力和有希望的表现。现有的自我监督的DeNoising框架主要建立在同一理论基础上，在该基础上，Denoising模型必须是J-Invariant。但是，我们的分析表明，当前的理论和J不变可能导致降低性能的模型。在这项工作中，我们介绍了一种新颖的自我监督的denoising框架，介绍了noings2same。在noings2same中，提出了一种新的自我监督损失，该损失是通过得出典型监督损失的自我监督的上限来提出的。特别是，noings2same既不需要J不变性，也不需要有关噪声模型的额外信息，并且可以在更广泛的DeNoising应用程序中使用。我们在理论上和实验上分析了我们提出的噪声2。实验结果表明，我们的noings2same明显优于以前的自我监督的剥夺方法，在降低性能和训练效率方面。我们的代码可在https://github.com/divelab/noise2same上找到。
Self-supervised frameworks that learn denoising models with merely individual noisy images have shown strong capability and promising performance in various image denoising tasks. Existing self-supervised denoising frameworks are mostly built upon the same theoretical foundation, where the denoising models are required to be J-invariant. However, our analyses indicate that the current theory and the J-invariance may lead to denoising models with reduced performance. In this work, we introduce Noise2Same, a novel self-supervised denoising framework. In Noise2Same, a new self-supervised loss is proposed by deriving a self-supervised upper bound of the typical supervised loss. In particular, Noise2Same requires neither J-invariance nor extra information about the noise model and can be used in a wider range of denoising applications. We analyze our proposed Noise2Same both theoretically and experimentally. The experimental results show that our Noise2Same remarkably outperforms previous self-supervised denoising methods in terms of denoising performance and training efficiency. Our code is available at https://github.com/divelab/Noise2Same.
