SelfDZSR (ECCV 2022)

PyTorch implementation of Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations

1. Framework

Overall pipeline of proposed SelfDZSR in the training and testing phase.

In the training, the center part of the short-focus and telephoto image is cropped respectively as the input LR and Ref, and the whole telephoto image is taken as the GT. The auxiliary-LR is generated to guide the alignment of LR and Ref towards GT.
In the testing, SelfDZSR can be directly deployed to super-solve the whole short-focus image with the reference of the telephoto image.

2. Preparation and Datasets

Prerequisites
- Python 3.x and PyTorch 1.6.
- OpenCV, NumPy, Pillow, tqdm, lpips, scikit-image and tensorboardX.
Dataset
- Nikon camera images and CameraFusion dataset can be downloaded from this link.

3. Quick Start

3.1 Pre-trained models

For simplifying the training process, we provide the pre-trained models of feature extractors and auxiliary-LR generator. The models for Nikon camera images and CameraFusion dataset are put in the ./ckpt/nikon_pretrain_models/ and ./ckpt/camerafusion_pretrain_models/ folder, respectively.
For direct testing, we provide the four pre-trained DZSR models (nikon_l1, nikon_l1sw, camerafusion_l1 and camerafusion_l1sw) in the ./ckpt/ folder. Taking nikon_l1sw as an example, it represents the model trained on the Nikon camera images using $l_1$ and sliced Wasserstein (SW) loss terms.

3.2 Training

For Nikon camera images, modify dataroot in train_nikon.sh and then run:

sh train_nikon.sh
For CameraFusion dataset, modify dataroot in train_camerafusion.sh and then run:

sh train_camerafusion.sh

3.3 Testing

For Nikon camera images, modify dataroot in test_nikon.sh and then run:

sh test_nikon.sh
For CameraFusion dataset, modify dataroot in test_camerafusion.sh and then run:

sh test_camerafusion.sh

3.4 Note

You can specify which GPU to use by --gpu_ids, e.g., --gpu_ids 0,1, --gpu_ids 3, --gpu_ids -1 (for CPU mode). In the default setting, all GPUs are used.
You can refer to options for more arguments.

4. Citation

If you find it useful in your research, please consider citing:

@inproceedings{SelfDZSR,
    title={Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations},
    author={Zhang, Zhilu and Wang, Ruohao and Zhang, Hongzhi and Chen, Yunjin and Zuo, Wangmeng},
    booktitle={ECCV},
    year={2022}
}

5. Acknowledgement

This repo is built upon the framework of CycleGAN, and we borrow some code from C2-Matching and DCSR, thanks for their excellent work!

HITRainer / SelfDZSR