Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution
This work addresses image restoration problems for computer vision applications, representing an incremental advancement by adapting graph convolutional networks to image processing.
The paper tackled image restoration tasks by proposing an encoder-decoder network that converts feature maps into graph vertices to apply graph convolutions, resulting in significant performance boosts for deblurring and super-resolution.
Graph convolutional networks (GCNs) have achieved great success in dealing with data of non-Euclidean structures. Their success directly attributes to fitting graph structures effectively to data such as in social media and knowledge databases. For image processing applications, the use of graph structures and GCNs have not been fully explored. In this paper, we propose a novel encoder-decoder network with added graph convolutions by converting feature maps to vertexes of a pre-generated graph to synthetically construct graph-structured data. By doing this, we inexplicitly apply graph Laplacian regularization to the feature maps, making them more structured. The experiments show that it significantly boosts performance for image restoration tasks, including deblurring and super-resolution. We believe it opens up opportunities for GCN-based approaches in more applications.