xinntao/EDVR

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1577 stars · 313 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning image-processing video-processing computer-vision image-processing deep-learning machine-learning python cross-platform pytorch super-resolution video-restoration deblurring denoising edvr basicsr research-code gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="xinntao/EDVR")