Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 52 references that are in the map. First posted on arXiv 21 May 2021.
Builds on
30 of 52 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
- 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
- 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
- 2018Residual Dense Network for Image Super-Resolutioncited by 796
- 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
18 more
- 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
- 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
- 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
- 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
- 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
- 2020DeeperGCN: All You Need to Train Deeper GCNscited by 249
- 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
- 2018Graph networks as learnable physics engines for inference and controlcited by 242
- 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
- 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 205
- 2020Human-Aware Motion Deblurringcited by 174
- 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
- 2019Graph Wavelet Neural Networkcited by 131
- 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
- 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
- 2017Multi-Label Zero-Shot Learning with Structured Knowledge Graphscited by 72
- 2014Learning to Deblurcited by 66
- 2019Extreme Channel Prior Embedded Network for Dynamic Scene Deblurringcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.