Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network
This addresses the issue of applying deep learning to real-world super-resolution applications by improving efficiency, though it is incremental as it builds on existing residual networks.
The paper tackles the problem of heavy computation in deep learning for single-image super-resolution by proposing a lightweight cascading residual network, achieving performance comparable to state-of-the-art methods with fewer parameters and operations.
In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks. Despite their great performances, deep learning methods cannot be easily applied to real-world applications due to the requirement of heavy computation. In this paper, we address this issue by proposing an accurate and lightweight deep network for image super-resolution. In detail, we design an architecture that implements a cascading mechanism upon a residual network. We also present variant models of the proposed cascading residual network to further improve efficiency. Our extensive experiments show that even with much fewer parameters and operations, our models achieve performance comparable to that of state-of-the-art methods.