- Home
- Image Upscaling Software
- BSRGAN
On the recordRead 11 Oct 202620 facts
BSRGAN
BSRGAN · Computer Vision Lab, ETH Zurich, Switzerland · founded 2021
Plans and prices
BSRGAN
Free
Open-source PyTorch code and pretrained models; no paid plans listed
Read 11 Oct 2026 · github.com
On the record
- Batch processing
- Yesgithub.com · read 22 Sep 2026
- Blur
- The model uses isotropic and anisotropic Gaussian blur kernels in both high- and low-resolution spaces.github.com · read 11 Oct 2026
- Customization
- The degradation model can be modified by changing its parameter settings and adding degradation types for a particular application.github.com · read 11 Oct 2026
- Degradation order
- It randomly shuffles degradations instead of always applying blur, downsampling, and noise in a fixed pipeline.github.com · read 11 Oct 2026
- Downsampling
- Supported downsampling methods include nearest, bilinear, bicubic, and down-up-sampling.github.com · read 11 Oct 2026
- Input formats
- JPG, JPEG, PNG, PPM, BMP, TIFgithub.com · read 22 Sep 2026
- License
- The repository identifies its license as Apache-2.0.github.com · read 11 Oct 2026
- 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.github.com · read 11 Oct 2026
- Maximum scale
- 4xgithub.com · read 22 Sep 2026
- Noise
- The degradation model includes Gaussian noise, JPEG compression noise, and processed camera sensor noise.github.com · read 11 Oct 2026
- Pretrained models
- The project provides BSRGAN and BSRNet pretrained model files for download through Google Drive or Tencent Weiyun.github.com · read 11 Oct 2026
- Purpose
- BSRGAN is a PyTorch project for blind image super-resolution and practical degradation modeling.github.com · read 11 Oct 2026
- Research origin
- The project presents work titled “Designing a Practical Degradation Model for Deep Blind Image Super-Resolution,” accepted to ICCV 2021.github.com · read 11 Oct 2026
- Scale factors
- The repository notes trained BSRGAN models for scale factors 2 and 4.github.com · read 11 Oct 2026
- Support and integrations
- The page provides code, training instructions, and model download links, and does not list commercial support or product integrations.github.com · read 11 Oct 2026
- Training
- The instructions describe training BSRNet and BSRGAN with PyTorch DataParallel or DistributedDataParallel, including a four-GPU example.github.com · read 11 Oct 2026
- Training data
- Its degradation model synthesizes paired low- and high-quality training images from high-quality images.github.com · read 11 Oct 2026
- Upscaling method
- aigithub.com · read 22 Sep 2026
