Deep Fourier channel attention network (DFCAN) is a network created to transform low-resolution (LR) images to super-resolved (SR) images, published by Qiao, Chang and Li, Di and Guo, Yuting and Liu, Chong and Jiang, Tao and Dai, Qionghai and Li, Dong. The training is done using LR-SR image pairs, taking the LR images as input and obtaining an output as close to SR as posible.
An example of a low resolution - high resolution pair:
Try it here
This notebook is inspired from the Zero-Cost Deep-Learning to Enhance Microscopy project (ZeroCostDL4Mic) (https://github.com/HenriquesLab/DeepLearning_Collab/wiki) and was created by jointly developed by Ainhoa Serrano , Ignacio Arganda-Carreras and Roberto Santana Hermida.
This notebook is based on the following paper:
Evaluation and development of deep neural networks for image super-resolution in optical microscopy, by Chang Qiao, Di Li, Yuting Guo, Chong Liu, Tao Jiang, Qionghai Dai & Dong Li et al. in Nature Methods 2021, https://www.nature.com/articles/s41592-020-01048-5
The source code of this notebook can be found in: Source code