# VITA-Group/DeblurGANv2

[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang

Repository: https://github.com/VITA-Group/DeblurGANv2
Canonical: https://ross.abutalabs.com/products/deblurganv2
Language: Python
License: NOASSERTION
License Family: other
Topics: deblurgan, generative-adversarial-network, pytorch, deep-learning, iccv, iccv2019, low-level-vision, ukraine
Last push: 2022-07-14T15:36:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2580, "days_push": 1511, "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 1192, forks 289 (observed 2026-08-28T04:03:56.263246+00:00)

## What it is
Official PyTorch implementation of DeblurGAN-v2, an ICCV 2019 relativistic conditional GAN for single-image motion deblurring with a Feature Pyramid Network generator and swappable backbones. It achieves fast, high-quality deblurring and generalizes to broader image restoration tasks.

## Use cases
- remove motion blur from photos
- deblur images with a GAN in pytorch
- real-time video deblurring with lightweight backbones
- restore blurry noisy images
- benchmark image deblurring models on GoPro dataset

## When to choose
- you need state-of-the-art or fast motion deblurring in PyTorch
- you want a research baseline for image restoration
- you need flexible speed/quality tradeoffs via backbone choice

## When to avoid
- you need a production-supported product with active development
- you need non-PyTorch or non-GPU environments
- you need general photo editing beyond blur removal

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python
- tags: gan, deblurring, image-restoration, pytorch, iccv-2019, research-code, motion-deblur, linux, gpu

## Member repositories
- VITA-Group/DeblurGANv2 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.263246+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 2026-08-30T06:22:28.251701+00:00, confidence not recorded.
  - readme: https://github.com/VITA-Group/DeblurGANv2 (fetched 2026-08-28T04:03:56.263246+00:00, sha 9fd171ebded5)
- Data as of 2026-08-30T08:39:29.467469+00:00.