Back to Search
Start Over
Deep Graph-Convolutional Image Denoising.
- Source :
-
IEEE Transactions on Image Processing . 2020, Vol. 29, p8226-8237. 12p. - Publication Year :
- 2020
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
- Subjects :
- *IMAGE denoising
*CONVOLUTIONAL neural networks
*RANDOM noise theory
Subjects
Details
- Language :
- English
- ISSN :
- 10577149
- Volume :
- 29
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Image Processing
- Publication Type :
- Academic Journal
- Accession number :
- 170078558
- Full Text :
- https://doi.org/10.1109/TIP.2020.3013166