# XPixelGroup/BasicSR

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

Repository: https://github.com/XPixelGroup/BasicSR
Canonical: https://ross.abutalabs.com/products/basicsr
Homepage: https://basicsr.readthedocs.io/en/latest/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: basicsr, esrgan, edsr, rcan, edvr, srresnet, srgan, super-resolution, restoration, pytorch, stylegan2, dfdnet, basicvsr, swinir, ecbsr
Last push: 2024-07-21T04:16:22+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3058, "days_push": 773, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8367, forks 1407 (observed 2026-08-28T04:10:20.530705+00:00)

## What it is
BasicSR is an open-source PyTorch toolbox for image and video restoration tasks such as super-resolution, denoising, deblurring, and JPEG artifact removal. It includes implementations of many state-of-the-art models like EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, and ECBSR, with training and testing pipelines.

## Use cases
- upscale low-resolution images with deep learning
- remove noise from photos using neural networks
- deblur blurry images or video frames
- restore compressed JPEG images
- train a custom super-resolution model in PyTorch
- enhance video quality frame by frame
- benchmark image restoration models

## When to choose
- you need a PyTorch framework for training or evaluating image/video restoration models
- you want ready implementations of classic and SOTA super-resolution architectures
- you need both image and video restoration in one toolbox

## When to avoid
- you need a simple one-click GUI upscaler rather than a research toolbox
- your task is unrelated to restoration (e.g., generation-only or classification)
- you need non-PyTorch frameworks like TensorFlow or ONNX-only inference

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, image-processing, video-processing
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: super-resolution, image-restoration, pytorch, denoising, deblurring, esrgan, swinir, video-restoration, model-zoo, training-framework, gpu

## Member repositories
- XPixelGroup/BasicSR (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:20.530705+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:27:33.678182+00:00, confidence not recorded.
  - readme: https://github.com/XPixelGroup/BasicSR (fetched 2026-08-28T04:10:20.530705+00:00, sha afd9cd558520)
  - homepage: https://basicsr.readthedocs.io/en/latest/ (fetched 2026-08-29T08:27:26.861786+00:00, sha c21ed59806b2)
- Data as of 2026-08-30T08:39:29.467469+00:00.