BSRGAN icon indicating copy to clipboard operation
BSRGAN copied to clipboard

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

Results 22 BSRGAN issues
Sort by recently updated
recently updated
newest added

Is there any way to define patch size in main_test_bsrgan.py?

Thank you for sharing the code and model. Could you please share the trained model of x2 BSRNet? Thanks

导入add_jpeg_noise函数后,输出的图片是全黑的,怎么回事?

请问pretrained_netE 和pretrained_netD是同一个东西吗? 我填写如下 是否有问题 "root": "superresolution" // "denoising" | "superresolution" , "pretrained_netG": "bsrgan_x4_gan/models/BSRNet.pth" // path of pretrained model , "pretrained_netD": "bsrgan_x4_gan/models/vgg19-dcbb9e9d.pth" // path of pretrained model , "pretrained_netE": "bsrgan_x4_gan/models/vgg19-dcbb9e9d.pth" //...

Great work! Is there any plan releasing the DIV2k3D dataset or degradation model in the paper? Tks!

您好,您的网络模型很好,可以直接使用,想请问您,,是否有量化或者简化后的模型,可以在一般pc机上运行?谢谢

Hi Kai, thank you for your great work. And I want to know how to import the ISP model in the function "degradation_bsrgan_plus(img, sf=4, shuffle_prob=0.5, use_sharp=True, lq_patchsize=64, isp_model=None)" to process...

The model can be image denoised while SR, but in some scenarios, details are lost,has this happened during your test?for example original image ![03877](https://user-images.githubusercontent.com/44860428/165906264-fb4c9d8e-8e60-427b-b3e8-cd72b25189f8.png) SR image ![03877](https://user-images.githubusercontent.com/44860428/165906141-9f16d3c7-96aa-4730-898f-4ef8286d7f37.png) Tile texture features...

大佬,有几个问题想请教下: 1. 如果从头训练,需要准备多少张高清训练样本?(数据主要为电商平台的商品主图) 2. BSRNET和BSRGAN分别需要训练多少个epoch/iter,训练时长大概是多久? 3. 为什么要先训练BSRNET再训练BSRGAN?训练BSRGAN的时候只需要导入训好的BSRNET的XXX_G.pth吗? 麻烦大佬得空的时候解答下,万分感谢!

Hi, great work the results look really good. I had few questions regarding training 1. How long did you train the BSRNet? 2. Did you apply the proposed data degradation...