GitHub - rakshita111/Layout-to-Image-Synthesis: This is a modified version of LostGAN-v2 with part-wise segmentation masks

This work is a modification of LostGAN-v2, where partwise segmentation masks are combined with the ISLA-Norm at the ResBlocks in the generator.

Results

Comparison of the images generated by LostGAN-v2 and the modified LostGAN

Visualization of the partmasks for generated images

Quantitative comparison of different layout-to-image synthesis methods on COCO-dataset (128x128 images)

Check INSTALL.md for installation instructions.

python train.py --dataset coco --out_path outputs/

python test.py --dataset coco --model_path pretrained_model/G_coco.pth --sample_path samples/coco/

The code is majorly borrowed from LostGAN-v2.

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
data		data
figures		figures
model		model
scripts		scripts
utils		utils
INSTALL.md		INSTALL.md
README.md		README.md
requirements.txt		requirements.txt
setup.py		setup.py
test.py		test.py
train.py		train.py