Enhanced Deep Residual Networks for Single Image Super-Resolution

TLDR

Recent research on super‑resolution has advanced with deep convolutional neural networks, and residual learning techniques have further improved performance. The authors aim to develop an enhanced deep super‑resolution network (EDSR) that surpasses current state‑of‑the‑art methods. They propose the EDSR architecture and a multi‑scale deep super‑resolution system (MDSR) with a novel training method that reconstructs high‑resolution images at multiple upscaling factors in a single model. The EDSR and MDSR models achieve significant performance gains by removing unnecessary modules, enlarging the network, stabilizing training, and outperform state‑of‑the‑art methods on benchmark datasets, winning the NTIRE2017 Super‑Resolution Challenge.

Abstract

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance. In this paper, we develop an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods. The significant performance improvement of our model is due to optimization by removing unnecessary modules in conventional residual networks. The performance is further improved by expanding the model size while we stabilize the training procedure. We also propose a new multi-scale deep super-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model. The proposed methods show superior performance over the state-of-the-art methods on benchmark datasets and prove its excellence by winning the NTIRE2017 Super-Resolution Challenge[26].