# LoSealL/VideoSuperResolution

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.

Repository: https://github.com/LoSealL/VideoSuperResolution
Canonical: https://ross.abutalabs.com/products/videosuperresolution
Language: Python
License: MIT
License Family: permissive
Topics: super-resolution, tensorflow, srcnn, dncnn, vdsr, srgan, rdn, srmd, dbpn, edsr, carn, rcan, vespcn, vsr, frvsr, pytorch, ntire2019
Last push: 2020-09-11T14:36:45+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3012, "days_push": 2182, "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 1687, forks 295 (observed 2026-08-28T04:05:22.216061+00:00)

## What it is
A Python library (pip-installable as VSR) collecting reimplementation of state-of-the-art single-image and video super-resolution neural network architectures in TensorFlow, with some PyTorch ports. It includes many classic models such as SRCNN, VDSR, EDSR, SRGAN, and DBPN, some with downloadable pretrained weights.

## Use cases
- upscale low-resolution videos with deep learning
- enhance resolution of single images using SR models
- compare super-resolution architectures like EDSR and SRGAN
- reproduce benchmark results from NTIRE super-resolution papers
- run pretrained super-resolution models in TensorFlow
- experiment with video super-resolution networks like VESPCN

## When to choose
- you want many SR architectures implemented in one consistent framework
- you need a pip-installable super-resolution library with pretrained weights
- you are researching or benchmarking image/video upscaling models

## When to avoid
- you need production-grade, actively maintained upscaling software
- you require the latest 2021+ architectures or GPU-optimized inference
- you work outside Python/TensorFlow ecosystems

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, video-processing, deep-learning
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: super-resolution, tensorflow, pytorch, srgan, edsr, vdsr, video-upscaling, image-upscaling, pretrained-models, video

## Member repositories
- LoSealL/VideoSuperResolution (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:22.216061+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 2026-08-30T03:38:50.429230+00:00, confidence not recorded.
  - readme: https://github.com/LoSealL/VideoSuperResolution (fetched 2026-08-28T04:05:22.216061+00:00, sha 8b99e356754a)
- Data as of 2026-08-30T08:39:29.467469+00:00.