Bringing Old Photos Back to Life
This work addresses the restoration of real old photos with complex, mixed degradations, which is a domain-specific problem for digital preservation and archival applications, though it builds incrementally on existing translation and VAE methods.
The authors tackled the problem of restoring severely degraded old photos by proposing a triplet domain translation network that uses synthetic image pairs and two variational autoencoders to close the domain gap in latent spaces, achieving state-of-the-art visual quality improvements.
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.