# Deep Graph-Convolutional Image Denoising

arXiv: https://arxiv.org/abs/1907.08448 · HTML: https://mlsanity.com/paper/1907.08448/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2019.

## Built on by (most cited first, 30 of 32)

- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [Multimodal learning with graphs](https://mlsanity.com/paper/2209.03299/) (2022)
- [Dynamic Attentive Graph Learning for Image Restoration](https://mlsanity.com/paper/2109.06620/) (2021)
- [Learning Frequency-aware Dynamic Network for Efficient Super-Resolution](https://mlsanity.com/paper/2103.08357/) (2021)
- [Optimization-Induced Graph Implicit Nonlinear Diffusion](https://mlsanity.com/paper/2206.14418/) (2022)
- [Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion](https://mlsanity.com/paper/2108.06073/) (2021)
- [Image Compressed Sensing Using Non-local Neural Network](https://mlsanity.com/paper/2112.03712/) (2021)
- [A Comparison of Image Denoising Methods](https://mlsanity.com/paper/2304.08990/) (2023)
- [Spatial-Frequency Attention for Image Denoising](https://mlsanity.com/paper/2302.13598/) (2023)
- [All-optical image denoising using a diffractive visual processor](https://mlsanity.com/paper/2309.09215/) (2023)
- [A cross Transformer for image denoising](https://mlsanity.com/paper/2310.10408/) (2023)
- [DEALing with Image Reconstruction: Deep Attentive Least Squares](https://mlsanity.com/paper/2502.04079/) (2025)
- [Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond](https://mlsanity.com/paper/2201.10084/) (2022)
- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling](https://mlsanity.com/paper/2310.10033/) (2023)
- [Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical](https://mlsanity.com/paper/2109.02219/) (2021)
- [DDT: Dual-branch Deformable Transformer for Image Denoising](https://mlsanity.com/paper/2304.06346/) (2023)
- [CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing](https://mlsanity.com/paper/2112.00913/) (2021)
- [How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices](https://mlsanity.com/paper/2603.05010/) (2026)
- [Reinforcement Learning of Self Enhancing Camera Image and Signal Processing](https://mlsanity.com/paper/2111.07499/) (2021)
- [Deep Image Semantic Communication Model for Artificial Intelligent Internet of Things](https://mlsanity.com/paper/2311.02926/) (2023)
- [VibrantLeaves: A principled parametric image generator for training deep restoration models](https://mlsanity.com/paper/2504.10201/) (2025)
- [Deep Learning strategies for ProtoDUNE raw data denoising](https://mlsanity.com/paper/2103.01596/) (2021)
- [Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing](https://mlsanity.com/paper/2104.00253/) (2021)
- [GCN-MIF: Graph Convolutional Network with Multi-Information Fusion for Low-dose CT Denoising](https://mlsanity.com/paper/2105.07146/) (2021)
- [Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution](https://mlsanity.com/paper/2208.02861/) (2022)
- [Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN](https://mlsanity.com/paper/2210.11174/) (2022)
- [A deep convolutional neural network for salt-and-pepper noise removal using selective convolutional blocks](https://mlsanity.com/paper/2302.05435/) (2023)
- [Multi-level Attention-guided Graph Neural Network for Image Restoration](https://mlsanity.com/paper/2502.19181/) (2025)

## Abstract (arXiv)

Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite only exploiting local information. In this paper, we propose a novel end-to-end trainable neural network architecture employing layers based on graph convolution operations, thereby creating neurons with non-local receptive fields. The graph convolution operation generalizes the classic convolution to arbitrary graphs. In this work, the graph is dynamically computed from similarities among the hidden features of the network, so that the powerful representation learning capabilities of the network are exploited to uncover self-similar patterns. We introduce a lightweight Edge-Conditioned Convolution which addresses vanishing gradient and over-parameterization issues of this particular graph convolution. Extensive experiments show state-of-the-art performance with improved qualitative and quantitative results on both synthetic Gaussian noise and real noise.