Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single noisy images, solve the data collection problem. However, self-supervised denoising methods, especially blindspot-driven ones, suffer sizable information loss during input or network design. The absence of valuable information dramatically reduces the upper bound of denoising performance. In this paper, we propose a simple yet efficient approach called Blind2Unblind to overcome the information loss in blindspot-driven denoising methods. First, we introduce a global-aware mask mapper that enables global perception and accelerates training. The mask mapper samples all pixels at blind spots on denoised volumes and maps them to the same channel, allowing the loss function to optimize all blind spots at once. Second, we propose a re-visible loss to train the denoising network and make blind spots visible. The denoiser can learn directly from raw noise images without losing information or being trapped in identity mapping. We also theoretically analyze the convergence of the re-visible loss. Extensive experiments on synthetic and real-world datasets demonstrate the superior performance of our approach compared to previous work. Code is available at https://github.com/demonsjin/Blind2Unblind.

翻译：大规模真实噪声-干净配对数据成本高昂且难以获取。同时，在合成数据上训练的监督去噪器在实际应用中表现不佳。自监督去噪器仅从单张噪声图像中学习，解决了数据采集问题。然而，自监督去噪方法，尤其是盲点驱动方法，在输入或网络设计过程中会遭受显著的信息损失。有价值信息的缺失极大地降低了去噪性能的上限。本文提出了一种名为Blind2Unblind的简单而高效的方法，以克服盲点驱动去噪方法中的信息损失。首先，我们引入了一个全局感知掩码映射器，实现了全局感知并加速了训练。该掩码映射器在去噪体积上对所有盲点像素进行采样，并将其映射到同一通道，使得损失函数能够一次性优化所有盲点。其次，我们提出了一种重新可见损失来训练去噪网络，并使盲点变得可见。去噪器可以直接从原始噪声图像中学习，而不会损失信息或陷入恒等映射。我们还从理论上分析了重新可见损失的收敛性。在合成和真实数据集上的大量实验表明，与之前的工作相比，我们的方法具有优越的性能。代码可在 https://github.com/demonsjin/Blind2Unblind 获取。