Convolutional neural networks have been proven 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 their performance deteriorates drastically when applied to other degradation settings. In this paper, we propose deep likelihood network (DL-Net), aiming at generalizing off-the-shelf image restoration networks to succeed over a spectrum of degradation levels. We slightly modify an off-the-shelf network by appending a simple recursive module, which is derived from a fidelity term, for disentangling the computation for multiple degradation levels. Extensive experimental results on image inpainting, interpolation, and super-resolution show the effectiveness of our DL-Net.

中文翻译：

---

具有多个降级的深度似然网络用于图像恢复

卷积神经网络已被证明可以有效地完成各种图像恢复任务。但是，大多数最新解决方案都是使用具有单个特定降级级别的图像进行训练的，当将其应用于其他降级设置时，其性能会急剧下降。在本文中，我们提出了深度似然网络（DL-Net），旨在推广现成的图像恢复网络以在一系列退化水平上取得成功。我们通过附加一个简单的递归模块（从保真度术语派生）来稍微修改现成的网络，以解开多个降级级别的计算。在图像修复，插值和超分辨率方面的大量实验结果证明了我们的DL-Net的有效性。