Teacher-Student Network for Real-World Face Super-Resolution with Progressive Embedding of Edge Information
This work addresses the domain gap issue in real-world face super-resolution, which is important for applications like surveillance or photography, but it appears incremental as it builds on existing teacher-student and edge information techniques.
The paper tackles the problem of poor generalization in face super-resolution (FSR) methods when applied to real-world images by proposing a teacher-student model that addresses domain gaps and progressively embeds edge information. The result is a method that surpasses state-of-the-art approaches in producing high-quality face images for real-world FSR, as demonstrated through extensive experiments.
Traditional face super-resolution (FSR) methods trained on synthetic datasets usually have poor generalization ability for real-world face images. Recent work has utilized complex degradation models or training networks to simulate the real degradation process, but this limits the performance of these methods due to the domain differences that still exist between the generated low-resolution images and the real low-resolution images. Moreover, because of the existence of a domain gap, the semantic feature information of the target domain may be affected when synthetic data and real data are utilized to train super-resolution models simultaneously. In this study, a real-world face super-resolution teacher-student model is proposed, which considers the domain gap between real and synthetic data and progressively includes diverse edge information by using the recurrent network's intermediate outputs. Extensive experiments demonstrate that our proposed approach surpasses state-of-the-art methods in obtaining high-quality face images for real-world FSR.