Near Infrared Image colorization
Implementation of Infrared image colorization using S-shape network.
Original structure of colorization process
Idea was derived from Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification
By utilizing this global feature fusions, I hope to get a more universal result
Infrared image colorization paper example
Adding global feature fusion model, result from dataset scene
Also I test on Loveday dataset
Train and Test process can be found in Unet_Train_Test.ipynb.
The modification of model can be found in unet_model2.py and unet_part2.py