The vast work in Deep Learning (DL) has led to a leap in image denoising research. Most DL solutions for this task have chosen to put their efforts on the denoiser's architecture while maximizing distortion performance. However, distortion driven solutions lead to blurry results with sub-optimal perceptual quality, especially in immoderate noise levels. In this paper we propose a different perspective, aiming to produce sharp and visually pleasing denoised images that are still faithful to their clean sources. Formally, our goal is to achieve high perceptual quality with acceptable distortion. This is attained by a stochastic denoiser that samples from the posterior distribution, trained as a generator in the framework of conditional generative adversarial networks (CGAN). Contrary to distortion-based regularization terms that conflict with perceptual quality, we introduce to the CGAN objective a theoretically founded penalty term that does not force a distortion requirement on individual samples, but rather on their mean. We showcase our proposed method with a novel denoiser architecture that achieves the reformed denoising goal and produces vivid and diverse outcomes in immoderate noise levels.
翻译:深层学习(DL)的庞大工作导致图像解密研究的飞跃。 大部分DL的解决方案都选择将其精力放在去掉的建筑上,同时最大限度地提高扭曲性表现。 然而,扭曲性驱动的解决方案导致非最佳感知质量的模糊结果,特别是在中度噪音水平方面。 在本文中,我们提出了一个不同的观点, 目的是生成仍然忠实于其清洁来源的清晰和视觉上令人愉快的去光化图像。 形式上, 我们的目标是以可接受的扭曲方式实现高感知质量。 实现这一目的的, 是通过从后方分布中提取的样本, 在有条件的基因对抗网络( CGAN) 框架内培训为生成者。 与基于扭曲性的正规化术语相冲突的相反, 我们向CGAN 目标引入了一个理论化的惩罚术语, 该术语不会迫使对单个样本的扭曲性要求,而是其平均值。 我们用一个创新的去色化架构展示了我们的拟议方法,该方法实现了改革的去除性目标, 并产生了在衣着层噪音的噪音水平上产生生动和多样化的结果。