# xinntao/EDVR

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR and this repo is a mirror of BasicSR.

Repository: https://github.com/xinntao/EDVR
Canonical: https://ross.abutalabs.com/products/edvr
Homepage: https://github.com/xinntao/BasicSR
Language: Python
License Family: other
Topics: basicsr, edvr, pytorch
Last push: 2021-08-09T14:20:10+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": 2703, "days_push": 1850, "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 1577, forks 313 (observed 2026-08-28T04:05:06.224323+00:00)

## What it is
EDVR is the winning solution of the NTIRE19 video restoration challenges, built on enhanced deformable convolutional networks. The repo is now a mirror of BasicSR, an open-source PyTorch image and video restoration toolbox covering super-resolution, denoising, deblurring, and JPEG artifact removal.

## Use cases
- restore and enhance low-quality videos with deep learning
- super-resolve images with ESRGAN or SwinIR
- denoise or deblur video frames
- remove JPEG compression artifacts from images
- train custom restoration models in PyTorch
- reproduce NTIRE19 challenge-winning video restoration results

## When to choose
- you need state-of-the-art video restoration or super-resolution models with pretrained weights
- you want a PyTorch toolbox for training and benchmarking restoration networks
- you are doing research on deformable convolutions or video enhancement

## When to avoid
- you want active development on this specific repo - use BasicSR instead since EDVR was merged there
- you need a production-ready end-user application rather than a research codebase
- you lack a GPU, since training and inference are compute-intensive

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, video-processing
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: pytorch, super-resolution, video-restoration, deblurring, denoising, edvr, basicsr, research-code, gpu, linux

## Member repositories
- xinntao/EDVR (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:06.224323+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 2026-08-30T03:57:11.551737+00:00, confidence not recorded.
  - readme: https://github.com/xinntao/EDVR (fetched 2026-08-28T04:05:06.224323+00:00, sha 4aa5b054ea68)
  - homepage: https://github.com/xinntao/BasicSR (fetched 2026-08-29T11:27:36.635622+00:00, sha 5d2ec73c7496)
- Data as of 2026-08-30T08:39:29.467469+00:00.