Although the advances of self-supervised blind denoising are significantly superior to conventional approaches without clean supervision in synthetic noise scenarios, it shows poor quality in real-world images due to spatially correlated noise corruption. Recently, pixel-shuffle downsampling (PD) has been proposed to eliminate the spatial correlation of noise. A study combining a blind spot network (BSN) and asymmetric PD (AP) successfully demonstrated that self-supervised blind denoising is applicable to real-world noisy images. However, PD-based inference may degrade texture details in the testing phase because high-frequency details (e.g., edges) are destroyed in the downsampled images. To avoid such an issue, we propose self-residual learning without the PD process to maintain texture information. We also propose an order-variant PD constraint, noise prior loss, and an efficient inference scheme (progressive random-replacing refinement ($\text{PR}^3$)) to boost overall performance. The results of extensive experiments show that the proposed method outperforms state-of-the-art self-supervised blind denoising approaches, including several supervised learning methods, in terms of PSNR, SSIM, LPIPS, and DISTS in real-world sRGB images.

翻译：尽管自监督盲去噪在合成噪声场景下显著优于传统无干净监督方法，但由于真实图像中存在空间相关噪声污染，其表现质量低下。近期提出的像素洗牌下采样（PD）技术可消除噪声的空间相关性。将盲点网络（BSN）与非对称PD（AP）相结合的研究已成功证明，自监督盲去噪可应用于真实噪声图像。然而，基于PD的推理在测试阶段会因高频细节（如边缘）在下采样图像中被破坏而降质纹理细节。为解决该问题，我们提出无需PD过程的自残差学习方法以保持纹理信息。同时，我们提出顺序变异PD约束、噪声先验损失及高效推理方案——渐进式随机替换精炼（$\text{PR}^3$）以提升整体性能。大量实验结果表明，在真实sRGB图像上，就PSNR、SSIM、LPIPS及DISTS指标而言，所提方法优于现有最优自监督盲去噪方法，甚至包括若干监督学习方法。