This is the official implementation of the papaer (under review):
GCT-GF: A generative CNN-transformer for multi-modal multi-temporal gap filling of surface water probability
Please use train.sh and test.sh to train and test the algorithm.
This research is based on the open source codes as follows:
SEN12-MS-CR-TS: [https://github.com/PatrickTUM/SEN12MS-CR-TS.git]
Gated Convolution: [https://github.com/JiahuiYu/generative_inpainting.git]
Restormer: [https://github.com/swz30/Restormer.git]
Thank these authors for their contributions to the community.