Online Learning for Reference-Based Super-Resolution

Online learning is a method for exploiting input data to update deep networks in the test stage to derive potential performance improvement. Existing online learning methods for single-image super-resolution (SISR) utilize an input low-resolution (LR) image for the online adaptation of deep networks. Unlike SISR approaches, reference-based super-resolution (RefSR) algorithms benefit from an additional high-resolution (HR) reference image containing plenty of useful features for enhancing the input LR image. Therefore, we introduce a new online learning algorithm, using several reference images, which is applicable to not only RefSR but also SISR networks. Experimental results show that our online learning method is seamlessly applicable to many existing RefSR and SISR models, and that improves performance. We further present the robustness of our method to non-bicubic degradation kernels with in-depth analyses.

Automated summary

Online learning is a method used to update deep networks with input data in order to improve potential performance. A new online learning algorithm is introduced in this research, utilizing multiple reference images for both RefSR and SISR networks, showing improved performance and robustness to different degradation kernels. Experimental results demonstrate the seamless applicability of this online learning method to existing RefSR and SISR models.