论文标题
通过关节学习处理图像降解中的噪声
Handling noise in image deblurring via joint learning
论文作者
论文摘要
当前，许多盲目的脱毛方法都假定模糊的图像是无噪声的，并且在带有噪声的模糊图像上表现不令人满意。不幸的是，在真实场景中，噪音很普遍。一个简单的解决方案是在去除图像之前将图像变形。但是，即使是最先进的Denoisers也无法保证完全消除噪音。在变性的图像中，轻微的残留噪声可能会在脱毛阶段引起大量伪影。为了解决这个问题，我们提出了一个级联的框架，该框架由Denoiser子网和Deblurring子网组成。与以前的方法相反，我们共同训练两个子网。联合学习减少了降解对脱毛后残留噪声的影响，因此改善了脱毛对沉重噪声的鲁棒性。此外，我们的方法也有助于模糊内核估计。 Celeba数据集和GOPRO数据集的实验表明，我们的方法对几种最新方法的表现有利。
Currently, many blind deblurring methods assume blurred images are noise-free and perform unsatisfactorily on the blurry images with noise. Unfortunately, noise is quite common in real scenes. A straightforward solution is to denoise images before deblurring them. However, even state-of-the-art denoisers cannot guarantee to remove noise entirely. Slight residual noise in the denoised images could cause significant artifacts in the deblurring stage. To tackle this problem, we propose a cascaded framework consisting of a denoiser subnetwork and a deblurring subnetwork. In contrast to previous methods, we train the two subnetworks jointly. Joint learning reduces the effect of the residual noise after denoising on deblurring, hence improves the robustness of deblurring to heavy noise. Moreover, our method is also helpful for blur kernel estimation. Experiments on the CelebA dataset and the GOPRO dataset show that our method performs favorably against several state-of-the-art methods.
