Accurate Image Super-Resolution Using Very Deep Convolutional Networks
Abstract¶
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.
Summary¶
VDSR shows that much deeper CNNs can improve single-image super-resolution when trained as residual predictors with aggressive learning rates and gradient clipping. It marks an important transition from shallow SRCNN-style mappings to deeper residual restoration networks.