Abstract
Convolutional neural networks have been proven very effective in a variety of image restoration tasks. Most state-of-the-art solutions, however, are trained using images with a single particular degradation level, and can deteriorate drastically when being applied to some other degradation settings. In this paper, we propose a novel method dubbed deep likelihood network (DL-Net), aiming at generalizing off-the-shelf image restoration networks to succeed over a spectrum of degradation settings while keeping their original learning objectives and core architectures. In particular, we slightly modify the original restoration networks by appending a simple yet effective recursive module, which is derived from a fidelity term for disentangling the effect of degradations. Extensive experimental results on image inpainting, interpolation and super-resolution demonstrate the effectiveness of our DL-Net.
Abstract (translated)
卷积神经网络已被证明是非常有效的各种图像恢复任务。然而,大多数最先进的解决方案都是使用具有单一特定降级级别的图像进行培训的,当应用于其他降级设置时,这些解决方案可能会急剧恶化。本文提出了一种称为深似然网络(dl-net)的新方法,在保持原有学习目标和核心体系结构的前提下,推广现成的图像恢复网络,使其在一定的退化背景下获得成功。特别是,我们通过附加一个简单而有效的递归模块来稍微修改原始恢复网络,这个模块是从一个消除退化影响的保真度术语派生而来的。大量的图像修复、插值和超分辨率实验结果证明了我们的DL网络的有效性。
URL
https://arxiv.org/abs/1904.09105