LSR: A Light-Weight Super-Resolution Method
This work addresses the need for efficient super-resolution on mobile/edge platforms, though it appears incremental as it builds on existing residual prediction and self-supervised approaches.
The paper tackles the problem of single-image super-resolution for mobile applications by proposing a light-weight method (LSR) that predicts residual images using a self-supervised framework, achieving better visual quality than classical exemplar-based methods in terms of PSNR/SSIM measures.
A light-weight super-resolution (LSR) method from a single image targeting mobile applications is proposed in this work. LSR predicts the residual image between the interpolated low-resolution (ILR) and high-resolution (HR) images using a self-supervised framework. To lower the computational complexity, LSR does not adopt the end-to-end optimization deep networks. It consists of three modules: 1) generation of a pool of rich and diversified representations in the neighborhood of a target pixel via unsupervised learning, 2) selecting a subset from the representation pool that is most relevant to the underlying super-resolution task automatically via supervised learning, 3) predicting the residual of the target pixel via regression. LSR has low computational complexity and reasonable model size so that it can be implemented on mobile/edge platforms conveniently. Besides, it offers better visual quality than classical exemplar-based methods in terms of PSNR/SSIM measures.