This repository contains an op-for-op PyTorch reimplementation of Perceptual Extreme Super Resolution Network with Receptive Field Block.
Contains DIV2K, DIV8K, Flickr2K, OST, T91, Set5, Set14, BSDS100 and BSDS200, etc.
Both training and testing only need to modify the config.py file.
- line 31:
upscale_factorchange to16. - line 33:
modechange tovalid. - line 111:
model_pathchange toresults/pretrained_models/RFBESRNet_x16-DFO2K-0bcd554c.pth.tar.
- line 31:
upscale_factorchange to16. - line 33:
modechange totrain_rfbesrnet. - line 35:
exp_namechange toRFBESRNet_baseline.
- line 31:
upscale_factorchange to16. - line 33:
modechange totrain_rfbesrnet. - line 35:
exp_namechange toRFBESRNet_baseline. - line 49:
resumechange tosamples/RFBESRNet_baseline/g_epoch_xxx.pth.tar.
- line 31:
upscale_factorchange to16. - line 33:
modechange totrain_rfbesrgan. - line 35:
exp_namechange toRFBESRGAN_baseline. - line 77:
resumechange toresults/RFBESRNet_baseline/g_last.pth.tar.
- line 31:
upscale_factorchange to16. - line 33:
modechange totrain_rfbesrgan. - line 35:
exp_namechange toRFBESRGAN_baseline. - line 77:
resumechange toresults/RFBESRNet_baseline/g_last.pth.tar. - line 78:
resume_dchange tosamples/RFBESRGAN_baseline/g_epoch_xxx.pth.tar. - line 79:
resume_gchange tosamples/RFBESRGAN_baseline/g_epoch_xxx.pth.tar.
Source of original paper results: https://arxiv.org/pdf/2005.12597v1.pdf
In the following table, the value in () indicates the result of the project, and - indicates no test.
| Dataset | Scale | RFBNet (PSNR) | RFB_ESRGAN (PSNR) |
|---|---|---|---|
| DIV8K | 16 | (23.45) | 23.38(23.20) |
Low resolution / Recovered High Resolution / Ground Truth
If you find a bug, create a GitHub issue, or even better, submit a pull request. Similarly, if you have questions, simply post them as GitHub issues.
I look forward to seeing what the community does with these models!
Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo
Abstract
Perceptual Extreme Super-Resolution for single image is extremely difficult, because the texture details of different images vary greatly. To tackle
this difficulty, we develop a super resolution network with receptive field block based on Enhanced SRGAN. We call our network RFB-ESRGAN. The key
contributions are listed as follows. First, for the purpose of extracting multi-scale information and enhance the feature discriminability, we applied
receptive field block (RFB) to super resolution. RFB has achieved competitive results in object detection and classification. Second, instead of using
large convolution kernels in multi-scale receptive field block, several small kernels are used in RFB, which makes us be able to extract detailed
features and reduce the computation complexity. Third, we alternately use different upsampling methods in the upsampling stage to reduce the high
computation complexity and still remain satisfactory performance. Fourth, we use the ensemble of 10 models of different iteration to improve the
robustness of model and reduce the noise introduced by each individual model. Our experimental results show the superior performance of RFB-ESRGAN.
According to the preliminary results of NTIRE 2020 Perceptual Extreme Super-Resolution Challenge, our solution ranks first among all the participants.
@misc{2005.12597,
Author = {Taizhang Shang and Qiuju Dai and Shengchen Zhu and Tong Yang and Yandong Guo},
Title = {Perceptual Extreme Super Resolution Network with Receptive Field Block},
Year = {2020},
Eprint = {arXiv:2005.12597},
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent