Home

Awesome

RAW-to-sRGB (ICCV 2021)

PyTorch implementation of Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision

1. Framework

<p align="center"><img src="./figs/framework.png" width="95%"></p> <p align="center">Figure 1: Illustration of the proposed joint learning framework.</p>

2. Results

<p align="center"><img src="./figs/results.png" width="95%"></p> <p align="center">Figure 2: Example of data pairs of ZRR and SR-RAW datasets, where clear spatial misalignment can be observed with the reference line. With such inaccurately aligned training data, PyNet [22] and Zhang et al. [62] are prone to generating blurry results with spatial misalignment, while our results are well aligned with the input.</p>

3. Preparation

4. Quick Start

4.1 Pre-trained models

4.2 Training

4.3 Testing

4.4 Note

5. Citation

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

@inproceedings{RAW-to-sRGB,
    title={Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision},
    author={Zhang, Zhilu and Wang, Haolin and Liu, Ming and Wang, Ruohao and Zuo, Wangmeng and Zhang, Jiawei},
    booktitle={ICCV},
    year={2021}
}

6. Acknowledgement

This repo is built upon the framework of CycleGAN, and we borrow some code from PyNet, Zoom-Learn-Zoom, PWC-Net and AdaDSR, thanks for their excellent work!