Recently, denoising methods based on supervised learning have exhibited promising performance. However, their reliance on external datasets containing noisy-clean image pairs restricts their applicability. To address this limitation, researchers have focused on training denoising networks using solely a set of noisy inputs. To improve the feasibility of denoising procedures, in this study, we proposed a single-image self-supervised learning method in which only the noisy input image is used for network training. Gated convolution was used for feature extraction and no-reference image quality assessment was used for guiding the training process. Moreover, the proposed method sampled instances from the input image dataset using Bernoulli sampling with a certain dropout rate for training. The corresponding result was produced by averaging the generated predictions from various instances of the trained network with dropouts. The experimental results indicated that the proposed method achieved state-of-the-art denoising performance on both synthetic and real-world datasets. This highlights the effectiveness and practicality of our method as a potential solution for various noise removal tasks.

翻译：近期，基于监督学习的去噪方法展现出优越性能，但其依赖包含含噪-干净图像对的外部数据集，限制了应用范围。为解决这一局限，研究人员聚焦于仅利用含噪输入集训练去噪网络。为提升去噪流程的可行性，本研究提出一种单图像自监督学习方法，仅使用含噪输入图像进行网络训练。该方法采用门控卷积进行特征提取，并引入无参考图像质量评估指导训练过程。此外，所提方法通过伯努利采样以特定丢弃率从输入图像数据集中抽取实例进行训练，最终结果由对训练后网络（含丢弃操作）生成的多种预测取平均得到。实验表明，该算法在合成与真实数据集上均达到最先进的去噪性能，凸显其作为噪声去除任务潜在解决方案的有效性与实用性。