Papers › Deep Graph-Convolutional Image Denoising
Deep Graph-Convolutional Image Denoising
Diego Valsesia, Giulia Fracastoro, Enrico Magli
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Grayscale Image Denoising | BSD68 sigma15 | GCDN | PSNR | 31.83 | #7 of 16 | Archive leaderboard | report |
| Grayscale Image Denoising | BSD68 sigma25 | GCDN | PSNR | 29.35 | #6 of 16 | Archive leaderboard | report |
| Grayscale Image Denoising | BSD68 sigma50 | GCDN | PSNR | 26.38 | #10 of 15 | Archive leaderboard | report |
| Grayscale Image Denoising | Set12 sigma15 | GCDN | PSNR | 33.14 | #5 of 8 | Archive leaderboard | report |
| Grayscale Image Denoising | Set12 sigma25 | GCDN | PSNR | 30.78 | #4 of 6 | Archive leaderboard | report |
| Grayscale Image Denoising | Set12 sigma50 | GCDN | PSNR | 27.6 | #5 of 8 | Archive leaderboard | report |
| Grayscale Image Denoising | Urban100 sigma15 | GCDN | PSNR | 33.47 | #3 of 7 | Archive leaderboard | report |
| Grayscale Image Denoising | Urban100 sigma25 | GCDN | PSNR | 30.95 | #6 of 10 | Archive leaderboard | report |
| Grayscale Image Denoising | Urban100 sigma50 | GCDN | PSNR | 27.41 | #9 of 10 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections