让老照片回归生活（CS CV）---刘持诚

我们提出通过深度学习的方法，对严重退化的老照片进行修复。不同于传统的修复任务可以通过监督学习来解决，真实照片中的退化是复杂的，合成图像与真实老照片的领域差距使得网络无法泛化。因此，我们提出了一种新型的三重域翻译网络，通过利用真实照片与海量的合成图像组合来实现。具体来说，我们训练两个变分自动编码机（VAEs），分别将旧照片和干净照片转化为两个潜在空间。而这两个潜在空间之间的转换是通过合成配对数据来学习的。这种翻译可以很好地泛化为真实的照片，因为在紧凑的潜在空间中，域间隙是封闭的。此外，为了解决混杂在一张老照片中的多种退化，我们设计了一个带有 partial nonlocal block 的全局分支，用于处理结构性缺陷，如划痕、尘点等，和一个局部分支，用于处理非结构性缺陷，如噪点、模糊等。在隐空间内融合这两个分支，导致老照片的多重缺陷修复能力提高。

原文题目：Bringing Old Photos Back to Life

原文：We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent spaces. And the translation between these two latent spaces is learned with synthetic paired data. This translation generalizes well to real photos because the domain gap is closed in the compact latent space. Besides, to address multiple degradations mixed in one old photo, we design a global branch with a partial nonlocal block targeting to the structured defects, such as scratches and dust spots, and a local branch targeting to the unstructured defects, such as noises and blurriness. Two branches are fused in the latent space, leading to improved capability to restore old photos from multiple defects. The proposed method outperforms state-of-the-art methods in terms of visual quality for old photos restoration.

原文作者：Ziyu Wan, Bo Zhang, Dongdong Chen, Pan Zhang, Dong Chen, Jing Liao, Fang Wen

原文地址：https://arxiv.org/abs/2004.09484