Accurate Image Super-Resolution Using Very Deep Convolutional Networks
This work addresses the problem of enhancing image resolution for applications like photography and medical imaging, representing an incremental advance in deep learning-based super-resolution.
The authors tackled single-image super-resolution by using a very deep convolutional network with 20 layers, achieving significant accuracy improvements and better visual results compared to existing methods.
We present a highly accurate single-image super-resolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification \cite{simonyan2015very}. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers. By cascading small filters many times in a deep network structure, contextual information over large image regions is exploited in an efficient way. With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure. We learn residuals only and use extremely high learning rates ($10^4$ times higher than SRCNN \cite{dong2015image}) enabled by adjustable gradient clipping. Our proposed method performs better than existing methods in accuracy and visual improvements in our results are easily noticeable.