Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT
- Prepare your dataset under the directory 'data' in the CycleGAN or UNIT folder and set dataset name to parameter 'image_folder' in model init function.
- Directory structure on new dataset needed for training and testing:
- data/Dataset-name/trainA
- data/Dataset-name/trainB
- data/Dataset-name/testA
- data/Dataset-name/testB
- Train a model by:
python CycleGAN.py
or
python UNIT.py
- Generate synthetic images by following specifications under:
- CycleGAN/generate_images/ReadMe.md
- UNIT/generate_images/ReadMe.md
Left: Input image. Middle: Synthetic images generated during training. Right: Ground truth.
Histograms show pixel value distributions for synthetic images (blue) compared to ground truth (brown).
(An updated image normalization, present in the current version of this repo, has fixed the intensity error seen in these results.)
