Skip to content
SPECIFICTION
Get listed

BSRGAN

github.com

Free plan WindowsLinux
Visit github.com
Spec score 7.7 #66 of 99 in Image Upscaling Software

Spec sheet

Purpose
BSRGAN is a PyTorch project for blind image super-resolution and practical degradation modeling.Read 11 Oct 2026 · github.com
Free plan
YesRead 22 Sep 2026 · github.com
License
The repository identifies its license as Apache-2.0.Read 11 Oct 2026 · github.com
Founded
2021Read 28 Sep 2026 · github.com
Batch processing
YesRead 22 Sep 2026 · github.com
Blur
The model uses isotropic and anisotropic Gaussian blur kernels in both high- and low-resolution spaces.Read 11 Oct 2026 · github.com
Customization
The degradation model can be modified by changing its parameter settings and adding degradation types for a particular application.Read 11 Oct 2026 · github.com
Degradation order
It randomly shuffles degradations instead of always applying blur, downsampling, and noise in a fixed pipeline.Read 11 Oct 2026 · github.com
Downsampling
Supported downsampling methods include nearest, bilinear, bicubic, and down-up-sampling.Read 11 Oct 2026 · github.com
Input formats
JPG, JPEG, PNG, PPM, BMP, TIFRead 22 Sep 2026 · github.com
Limitation
The authors say the degradation model tends to be unsuited to model an already degraded low-resolution image because it has many parameters and uses random shuffling.Read 11 Oct 2026 · github.com
Maximum scale
4xRead 22 Sep 2026 · github.com
Noise
The degradation model includes Gaussian noise, JPEG compression noise, and processed camera sensor noise.Read 11 Oct 2026 · github.com
Pretrained models
The project provides BSRGAN and BSRNet pretrained model files for download through Google Drive or Tencent Weiyun.Read 11 Oct 2026 · github.com
Research origin
The project presents work titled “Designing a Practical Degradation Model for Deep Blind Image Super-Resolution,” accepted to ICCV 2021.Read 11 Oct 2026 · github.com
Scale factors
The repository notes trained BSRGAN models for scale factors 2 and 4.Read 11 Oct 2026 · github.com
Support and integrations
The page provides code, training instructions, and model download links, and does not list commercial support or product integrations.Read 11 Oct 2026 · github.com
Training
The instructions describe training BSRNet and BSRGAN with PyTorch DataParallel or DistributedDataParallel, including a four-GPU example.Read 11 Oct 2026 · github.com
Training data
Its degradation model synthesizes paired low- and high-quality training images from high-quality images.Read 11 Oct 2026 · github.com
Upscaling method
aiRead 22 Sep 2026 · github.com

Plans and prices

BSRGAN Free Open-source PyTorch code and pretrained models; no paid plans listed Read 11 Oct 2026 · github.com

Every BSRGAN plan and price →

Where Specifiction places it

Alternatives to BSRGANAll alternatives →