Train your own model for denoising and submit the denoised results to DND.
Typical result: sRGB track, PSNR > 39, SSIM > 0.95
Download the dataset (22 GB) (xmfw) and extract the files to ./data/ folder.
This repo provides the codes of DnCNN, U-Net and ResNet, but you can use your own model by adding it to ./model/ folder.
Train your model:
python train.py --model YourModelName
Optional arguments:
--model MODEL model name
--ps PS patch size
--lr LR learning rate
--epochs EPOCHS sum of epochs
--freq FREQ learning rate update frequency
--save_freq SAVE_FREQ save result frequency
--syn use synthetic noisy images
In order to reduce the time to read the images, it will save all the images in memory which requires large memory.
Test the trained model on DND and get the denoised results:
python submit.py --model YourModelName
The results are in ./result/test/bundled/.
- Guo, Shi, et al. "Toward convolutional blind denoising of real photographs." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.
- Anaya, Josue, and Adrian Barbu. "RENOIR–A dataset for real low-light image noise reduction." Journal of Visual Communication and Image Representation 51 (2018): 144-154.
- Abdelhamed, Abdelrahman, Stephen Lin, and Michael S. Brown. "A high-quality denoising dataset for smartphone cameras." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.
- Bychkovsky, Vladimir, et al. "Learning photographic global tonal adjustment with a database of input/output image pairs." CVPR 2011. IEEE, 2011.
- Plotz, Tobias, and Stefan Roth. "Benchmarking denoising algorithms with real photographs." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.