Here we provide the PyTorch implementation and pre-trained model of our latest version, if you require the code of our previous CVPR version ("Intrinsic Image Harmonization"), please click the release version.
- Linux
- Python 3
- CPU or NVIDIA GPU + CUDA CuDNN
- Download iHarmony4 dataset, and our HVIDIT dataset Google Drive or BaiduCloud (access code: akbi).
- Train
CUDA_VISIBLE_DEVICES=0 python train.py --model iih_base --name iih_base_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Test
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base --name iih_base_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Apply pre-trained model
Download pre-trained model from Google Drive or BaiduCloud (access code: n4js), and put latest_net_G.pth in the directory checkpoints/iih_base_allihd. Run:
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base --name iih_base_allihd --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Train
CUDA_VISIBLE_DEVICES=0 python train.py --model iih_base_lt --name iih_base_lt_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Test
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_lt --name iih_base_lt_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Apply pre-trained model
Download pre-trained model from Google Drive or BaiduCloud (access code: hqhw), and put latest_net_G.pth in the directory checkpoints/iih_base_lt_allihd. Run:
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_lt --name iih_base_lt_allihd --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Train
CUDA_VISIBLE_DEVICES=0 python train.py --model iih_base_gd --name iih_base_gd_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Test
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_gd --name iih_base_gd_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Apply pre-trained model
Download pre-trained model from Google Drive or BaiduCloud (access code: nqrc), and put latest_net_G.pth in the directory checkpoints/iih_base_gd_allihd. Run:
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_gd --name iih_base_gd_allihd --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Train
CUDA_VISIBLE_DEVICES=0 python train.py --model iih_base_lt_gd --name iih_base_lt_gd_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Test
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_lt_gd --name iih_base_lt_gd_allihd_test --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Apply pre-trained model
Download pre-trained model from Google Drive or BaiduCloud (access code: kmgp), and put latest_net_G.pth in the directory checkpoints/iih_base_lt_gd_allihd. Run:
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_lt_gd --name iih_base_lt_gd_allihd --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx- Train
CUDA_VISIBLE_DEVICES=0 python train.py --model iih_base_lt_gd --name iih_base_lt_gd_newihd_test --dataset_root <dataset_dir> --dataset_name newIHD --batch_size xx --init_port xxxx- Test
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_lt_gd --name iih_base_lt_gd_newihd_test --dataset_root <dataset_dir> --dataset_name newIHD --batch_size xx --init_port xxxx- Apply pre-trained model
Download pre-trained model from Google Drive or BaiduCloud (access code: jnhg), and put latest_net_G.pth in the directory checkpoints/iih_base_lt_gd_allihd. Run:
CUDA_VISIBLE_DEVICES=0 python test.py --model iih_base_lt_gd --name iih_base_lt_gd_newihd --dataset_root <dataset_dir> --dataset_name newIHD --batch_size xx --init_port xxxxWe provide the code in ih_evaluation.py. Run:
# iHarmony4 dataset
CUDA_VISIBLE_DEVICES=0 python evaluation/ih_evaluation.py --dataroot <dataset_dir> --result_root results/experiment/test_latest/images/ --evaluation_type our --dataset_name ALL
# iHarmony4 and HVIDIT datasets
CUDA_VISIBLE_DEVICES=0 python evaluation/ih_evaluation.py --dataroot <dataset_dir> --result_root results/experiment/test_latest/images/ --evaluation_type our --dataset_name newALL| Dataset | Metrics | Composite | Ours (iHarmony4) |
Ours (iHarmony4+HVIDIT) |
|---|---|---|---|---|
| HCOCO |
MSE PSNR SSIM fMSE fPSNR fSSIM |
69.37 33.99 0.9853 996.59 19.86 0.8257 |
21.61 37.82 0.9812 361.94 24.17 0.8736 |
21.51 37.81 0.9812 363.76 24.17 0.8735 |
| HAdobe5k |
MSE PSNR SSIM fMSE fPSNR fSSIM |
345.54 28.52 0.9483 2051.61 17.52 0.7295 |
40.67 36.61 0.9362 259.05 26.36 0.8413 |
39.27 36.60 0.9364 259.91 26.32 0.8407 |
| HFlickr |
MSE PSNR SSIM fMSE fPSNR fSSIM |
264.35 28.43 0.9620 1574.37 18.09 0.8036 |
94.91 32.10 0.9614 638.36 21.97 0.8444 |
94.25 32.06 0.9615 635.73 21.92 0.8436 |
| Hday2night |
MSE PSNR SSIM fMSE fPSNR fSSIM |
109.65 34.36 0.9607 1409.98 19.14 0.6353 |
51.44 37.06 0.9308 740.59 22.40 0.6585 |
59.87 36.42 0.9318 856.95 21.73 0.6549 |
| HVIDIT |
MSE PSNR SSIM fMSE fPSNR fSSIM |
53.12 38.72 0.9922 1604.41 19.01 0.7614 |
- - - - - |
25.51 41.43 0.9919 738.66 21.86 0.7139 |
| ALL |
MSE PSNR SSIM fMSE fPSNR fSSIM |
167.39 32.07 0.9724 1386.12 18.97 0.7905 |
35.90 36.81 0.9649 369.64 24.53 0.8571 |
35.09 36.99 0.9662 388.30 24.39 0.8506 |
More compared results can be found at Google Drive or BaduCloud (access code: lgs2).
If you use this code for your research, please cite our papers.
@InProceedings{Guo_2021_CVPR,
author = {Guo, Zonghui and Zheng, Haiyong and Jiang, Yufeng and Gu, Zhaorui and Zheng, Bing},
title = {Intrinsic Image Harmonization},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {16367-16376}
}
For some of the data modules and model functions used in this source code, we need to acknowledge the repo of DoveNet and CycleGAN.