Super-Resolution Models

EDSR: Enhanced Deep Residual Networks for Single Image Super-Resolution

Introduction

[ALGORITHM]

@inproceedings{lim2017enhanced,
  title={Enhanced deep residual networks for single image super-resolution},
  author={Lim, Bee and Son, Sanghyun and Kim, Heewon and Nah, Seungjun and Mu Lee, Kyoung},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition workshops},
  pages={136--144},
  year={2017}
}

Results and Models

Evaluated on RGB channels, scale pixels in each border are cropped before evaluation.

The metrics are PSNR / SSIM.

Method	Set5	Set14	DIV2K	Download
edsr_x2c64b16_1x16_300k_div2k	35.7592 / 0.9372	31.4290 / 0.8874	34.5896 / 0.9352	model | log
edsr_x3c64b16_1x16_300k_div2k	32.3301 / 0.8912	28.4125 / 0.8022	30.9154 / 0.8711	model | log
edsr_x4c64b16_1x16_300k_div2k	30.2223 / 0.8500	26.7870 / 0.7366	28.9675 / 0.8172	model | log

EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

Introduction

[ALGORITHM]

@InProceedings{wang2019edvr,
  author    = {Wang, Xintao and Chan, Kelvin C.K. and Yu, Ke and Dong, Chao and Loy, Chen Change},
  title     = {EDVR: Video restoration with enhanced deformable convolutional networks},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  month     = {June},
  year      = {2019},
}

Results and Models

Evaluated on RGB channels.

The metrics are PSNR / SSIM.

Method	REDS4	Download
edvrm_wotsa_x4_8x4_600k_reds	30.3430 / 0.8664	model | log
edvrm_x4_8x4_600k_reds	30.4194 / 0.8684	model | log

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

Introduction

[ALGORITHM]

@inproceedings{wang2018esrgan,
  title={Esrgan: Enhanced super-resolution generative adversarial networks},
  author={Wang, Xintao and Yu, Ke and Wu, Shixiang and Gu, Jinjin and Liu, Yihao and Dong, Chao and Qiao, Yu and Change Loy, Chen},
  booktitle={Proceedings of the European Conference on Computer Vision Workshops(ECCVW)},
  pages={0--0},
  year={2018}
}

Results and Models

Evaluated on RGB channels, scale pixels in each border are cropped before evaluation.

The metrics are PSNR / SSIM.

Method	Set5	Set14	DIV2K	Download
esrgan_psnr_x4c64b23g32_1x16_1000k_div2k	30.6428 / 0.8559	27.0543 / 0.7447	29.3354 / 0.8263	model | log
esrgan_x4c64b23g32_1x16_400k_div2k	28.2700 / 0.7778	24.6328 / 0.6491	26.6531 / 0.7340	model | log

Image Super-Resolution Using Deep Convolutional Networks

Introduction

[ALGORITHM]

@article{dong2015image,
  title={Image super-resolution using deep convolutional networks},
  author={Dong, Chao and Loy, Chen Change and He, Kaiming and Tang, Xiaoou},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={38},
  number={2},
  pages={295--307},
  year={2015},
  publisher={IEEE}
}

Results and Models

Evaluated on RGB channels, scale pixels in each border are cropped before evaluation.

The metrics are PSNR / SSIM.

Method	Set5	Set14	DIV2K	Download
srcnn_x4k915_1x16_1000k_div2k	28.4316 / 0.8099	25.6486 / 0.7014	27.7460 / 0.7854	model | log

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Introduction

[ALGORITHM]

@inproceedings{ledig2016photo,
  title={Photo-realistic single image super-resolution using a generative adversarial network},
  author={Ledig, Christian and Theis, Lucas and Husz{\'a}r, Ferenc and Caballero, Jose and Cunningham, Andrew and Acosta, Alejandro and Aitken, Andrew and Tejani, Alykhan and Totz, Johannes and Wang, Zehan},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition workshops},
  year={2016}
}

Results and Models

Evaluated on RGB channels, scale pixels in each border are cropped before evaluation.

The metrics are PSNR / SSIM.

Method	Set5	Set14	DIV2K	Download
msrresnet_x4c64b16_1x16_300k_div2k	30.2252 / 0.8491	26.7762 / 0.7369	28.9748 / 0.8178	model | log
srgan_x4c64b16_1x16_1000k_div2k	27.9499 / 0.7846	24.7383 / 0.6491	26.5697 / 0.7365	model | log

Video Enhancement with Task-oriented Flow

Introduction

[ALGORITHM]

@article{xue2019video,
  title={Video enhancement with task-oriented flow},
  author={Xue, Tianfan and Chen, Baian and Wu, Jiajun and Wei, Donglai and Freeman, William T},
  journal={International Journal of Computer Vision},
  volume={127},
  number={8},
  pages={1106--1125},
  year={2019},
  publisher={Springer}
}

Results and Models

Evaluated on RGB channels.

The metrics are PSNR / SSIM.

Method	Vid4	Download
tof_x4_vimeo90k_official	24.4377 / 0.7433	model