SelFSR: Self-Conditioned Face Super-Resolution in the Wild via Flow Field Degradation Network
This work addresses the problem of poor performance in real-world face super-resolution for applications like image enhancement, though it is incremental as it builds on existing degradation and conditioning methods.
The paper tackles the domain gap between synthetic training data and real-world images in face super-resolution by proposing a domain-adaptive degradation network that uses flow fields and a self-conditioned block, achieving state-of-the-art performance on CelebA and real-world datasets with improved identity consistency and perceptual quality.
In spite of the success on benchmark datasets, most advanced face super-resolution models perform poorly in real scenarios since the remarkable domain gap between the real images and the synthesized training pairs. To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild. This degradation network predicts a flow field along with an intermediate low resolution image. Then, the degraded counterpart is generated by warping the intermediate image. With the preference of capturing motion blur, such a model performs better at preserving identity consistency between the original images and the degraded. We further present the self-conditioned block for super-resolution network. This block takes the input image as a condition term to effectively utilize facial structure information, eliminating the reliance on explicit priors, e.g. facial landmarks or boundary. Our model achieves state-of-the-art performance on both CelebA and real-world face dataset. The former demonstrates the powerful generative ability of our proposed architecture while the latter shows great identity consistency and perceptual quality in real-world images.