GitHub - TAMU-VITA/DeblurGANv2: [ICCV 2019] "DeblurGAN-v2: Deblurring (Orde...
source link: https://github.com/TAMU-VITA/DeblurGANv2
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
Code for this paper DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
In ICCV 2019
Overview
We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility. DeblurGAN-v2 is based on a relativistic conditional GAN with a double-scale discriminator. For the first time, we introduce the Feature Pyramid Network into deblurring, as a core building block in the generator of DeblurGAN-v2. It can flexibly work with a wide range of backbones, to navigate the balance between performance and efficiency. The plug-in of sophisticated backbones (e.g., Inception-ResNet-v2) can lead to solid state-of-the-art deblurring. Meanwhile, with light-weight backbones (e.g., MobileNet and its variants), DeblurGAN-v2 reaches 10-100 times faster than the nearest competitors, while maintaining close to state-of-the-art results, implying the option of real-time video deblurring. We demonstrate that DeblurGAN-v2 obtains very competitive performance on several popular benchmarks, in terms of deblurring quality (both objective and subjective), as well as efficiency. Besides, we show the architecture to be effective for general image restoration tasks too.
DeblurGAN-v2 Architecture
Datasets
The Restore Dataset (DVD + GOPRO + NFS) used in the paper can be downloaded via the links below:
Training
Command
python train.py
training scirpt will load config under config/config.yaml
Tensorboard visualization
Yaml config structure
Testing
Command
Pre-trained models
Dataset G Model D Model Loss Type PSNR/ SSIM Link Restore Dataset Inception-ResNet-v2 double_gan ragan-ls 0.0/ 0.0 ModileNet double_gan ragan-ls 0.0/ 0.0 ModileNet-DSC double_gan ragan-ls 0.0/ 0.0Citation
If you use this code for your research, please cite our paper.
```
@InProceedings{Kupyn_2019_ICCV,
author = {Orest Kupyn and Tetiana Martyniuk and Junru Wu and Zhangyang Wang},
title = {DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2019}
}
```
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK