DENet: Disentangled Embedding Network for Visible Watermark Removal

This is official implementation for paper DENet: Disentangled Embedding Network for Visible Watermark Removal [AAAI2023 Oral]

Dataset preparation

|--data
|--|--LOGO
   |--|--10kmid
   |--|--10kgray
   |--|--10khigh

pip install -r requirements.txt

bash scripts/train_contrast_attention_on_logo_high.sh

bash scripts/train_contrast_attention_on_logo_mid.sh

bash scripts/train_contrast_attention_on_logo_gray.sh

bash scripts/test_LOGO_10khigh.sh

bash scripts/test_LOGO_10kmid.sh

bash scripts/test_LOGO_10kgray.sh

This code is mainly based on the previous work SLBR.

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
__pycache__		__pycache__
datasets		datasets
imgs		imgs
logs		logs
pytorch_iou		pytorch_iou
pytorch_ssim		pytorch_ssim
scripts		scripts
src		src
.gitignore		.gitignore
README.md		README.md
evaluation.py		evaluation.py
options.py		options.py
requirements.txt		requirements.txt
test.py		test.py
test_custom.py		test_custom.py
test_lpips.py		test_lpips.py
train.py		train.py