Two-stage domain adapted training for better generalization in real-world image restoration and super-resolution
This addresses generalization issues in real-world image restoration for applications like super-resolution, but it appears incremental as it builds on prior work mapping to intermediate domains.
The paper tackles the problem of neural networks overfitting to specific degradation models in inverse problems like image restoration, proposing a two-stage domain-adapted training strategy that first maps degraded images to an intermediate domain and then trains a second network for output. The result shows improved performance on both given and unseen degradation classes, though no concrete numbers are provided.
It is well-known that in inverse problems, end-to-end trained networks overfit the degradation model seen in the training set, i.e., they do not generalize to other types of degradations well. Recently, an approach to first map images downsampled by unknown filters to bicubicly downsampled look-alike images was proposed to successfully super-resolve such images. In this paper, we show that any inverse problem can be formulated by first mapping the input degraded images to an intermediate domain, and then training a second network to form output images from these intermediate images. Furthermore, the best intermediate domain may vary according to the task. Our experimental results demonstrate that this two-stage domain-adapted training strategy does not only achieve better results on a given class of unknown degradations but can also generalize to other unseen classes of degradations better.