# KupynOrest/DeblurGAN

Image Deblurring using Generative Adversarial Networks

Repository: https://github.com/KupynOrest/DeblurGAN
Canonical: https://ross.abutalabs.com/products/deblurgan
Language: Python
License: NOASSERTION
License Family: other
Topics: deep-learning, gan, deblurring, image-processing, image-manipulation, neural-network, convolutional-neural-networks, convolutional-networks, computer-vision, image-to-image-translation, blurry-images, pytorch, paper, pix2pix
Last push: 2019-12-25T18:40:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3416, "days_push": 2443, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2638, forks 531 (observed 2026-08-28T04:07:06.359730+00:00)

## What it is
A PyTorch implementation of the DeblurGAN paper for blind motion deblurring using conditional adversarial networks. It uses a Conditional Wasserstein GAN with gradient penalty and VGG-19 perceptual loss to convert blurry images into sharp estimates.

## Use cases
- deblur blurry photos with a GAN
- remove motion blur from images
- reproduce the DeblurGAN paper results
- train an image-to-image translation model in PyTorch
- adapt a conditional WGAN for super resolution or dehazing

## When to choose
- you need research-grade motion deblurring with pretrained weights
- you want a PyTorch GAN codebase to extend for image-to-image translation tasks
- you are reproducing or citing the DeblurGAN paper

## When to avoid
- you need CPU-only inference (untested)
- you want a production-ready, actively maintained deblurring product
- you need a permissively licensed library (license is non-standard)

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, computer-vision, deep-learning
- domain: computer-vision, image-processing, deep-learning
- platform: python
- tags: gan, deblurring, pytorch, image-to-image-translation, pix2pix, research-code, gpu

## Member repositories
- KupynOrest/DeblurGAN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.359730+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 2026-08-30T02:19:10.505649+00:00, confidence not recorded.
  - readme: https://github.com/KupynOrest/DeblurGAN (fetched 2026-08-28T04:07:06.359730+00:00, sha 7643881a341f)
- Data as of 2026-08-30T08:39:29.467469+00:00.