Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation (NeurIPS 2021)
by Qiming Hu, Xiaojie Guo.
- Python3
- PyTorch>=1.0
- OpenCV-Python, TensorboardX, Visdom
- NVIDIA GPU+CUDA
- 7,643 images from the Pascal VOC dataset, center-cropped as 224 x 224 slices to synthesize training pairs.
- 90 real-world training pairs provided by Zhang et al.
- 45 real-world testing images from CEILNet dataset.
- 20 real testing pairs provided by Zhang et al.
- 454 real testing pairs from SIR^2 dataset, containing three subsets (i.e., Objects (200), Postcard (199), Wild (55)).
- For stage 1:
python train_sirs.py --inet ytmt_ucs --model ytmt_model_sirs --name ytmt_ucs_sirs --hyper --if_align - For stage 2:
python train_twostage_sirs.py --inet ytmt_ucs --model twostage_ytmt_model --name ytmt_uct_sirs --hyper --if_align --resume --resume_epoch xx --checkpoints_dir xxx
python test_sirs.py --inet ytmt_ucs_old --model twostage_ytmt_model --name ytmt_uct_sirs_test --hyper --if_align --resume --icnn_path ./checkpoints/ytmt_uct_sirs/ytmt_uct_sirs_68_077_00595364.pt
Note: "ytmt_ucs_old" is only for our provided checkpoint, and please change it as "ytmt_ucs" when you train our model by yourself, since it is a refactorized verison for a better view.
400 images from the Berkeley segmentation dataset, following DnCNN.
python train_denoising.py --inet ytmt_pas --name ytmt_pas_denoising --preprocess True --num_of_layers 9 --mode B --preprocess True
python test_denoising.py --inet ytmt_pas --name ytmt_pas_denoising_blindtest_25 --test_noiseL 25 --num_of_layers 9 --test_data Set68 --icnn_path ./checkpoints/ytmt_pas_denoising_49_157500.pt
100 moireing and clean pairs from AIM 2019 Demoireing Challenge.
python train_demoire.py --inet ytmt_ucs --model ytmt_model_demoire --name ytmt_uas_demoire --hyper --if_align
python test_demoire.py --inet ytmt_ucs --model ytmt_model_demoire --name ytmt_uas_demoire_test --hyper --if_align --resume --icnn_path ./checkpoints/ytmt_ucs_demoire/ytmt_ucs_opt_086_00860000.pt
MIT-intrinsic dataset, pre-processed following Direct Intrinsics
python train_intrinsic.py --inet ytmt_ucs --model ytmt_model_intrinsic_decomp --name ytmt_ucs_intrinsic
python test_intrinsic.py --inet ytmt_ucs --model ytmt_model_intrinsic_decomp --name ytmt_ucs_intrinsic --resume --icnn_path [Path to your weight]