论文标题
通过隐式神经表示零射击盲图像denoing
Zero-shot Blind Image Denoising via Implicit Neural Representations
论文作者
论文摘要
基于“盲点”策略的最新deno算法显示出令人印象深刻的盲目图像降级性能，而无需使用任何外部数据集。虽然该方法在恢复高度污染的图像方面表现出色，但我们观察到在低噪声或真实噪声状态下，这种算法通常效率较低。为了解决这一差距，我们提出了一种基于我们的两个发现，我们提出了一种替代的剥落策略，该策略利用隐性神经表示（INR）的架构感应性偏见（INR）：（1）倾向于低频清洁图像信号比高频噪声更快地适合高频噪声，并且（2）InR层次更接近于高质量的InR层次更高的构成效果更高的效果更高的效果更高的效果。在这些观察结果的基础上，我们提出了一种脱氧算法，该算法通过惩罚更深的层重量的增长来最大程度地提高INR的先天性能力。我们表明，我们的方法在一组广泛的低噪声或现实情况下优于现有的零射击方法。
Recent denoising algorithms based on the "blind-spot" strategy show impressive blind image denoising performances, without utilizing any external dataset. While the methods excel in recovering highly contaminated images, we observe that such algorithms are often less effective under a low-noise or real noise regime. To address this gap, we propose an alternative denoising strategy that leverages the architectural inductive bias of implicit neural representations (INRs), based on our two findings: (1) INR tends to fit the low-frequency clean image signal faster than the high-frequency noise, and (2) INR layers that are closer to the output play more critical roles in fitting higher-frequency parts. Building on these observations, we propose a denoising algorithm that maximizes the innate denoising capability of INRs by penalizing the growth of deeper layer weights. We show that our method outperforms existing zero-shot denoising methods under an extensive set of low-noise or real-noise scenarios.
