# wenbihan/reproducible-image-denoising-state-of-the-art

Collection of popular and reproducible image denoising works.

Repository: https://github.com/wenbihan/reproducible-image-denoising-state-of-the-art
Canonical: https://ross.abutalabs.com/products/reproducible-image-denoising-state-of-the-art
License Family: other
Topics: image-denoising, benchmarking, state-of-the-art, reproducible-research, implementation, curated-list, summary, inverse-problems, image-restoration, image-processing, performance-analysis, image-reconstruction, noise, noise-reduction, recovery-image, denoising-algorithms, deep-learning, cnn, arxiv, art
Last push: 2021-12-05T04:47:48+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": 3168, "days_push": 1732, "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 2516, forks 506 (observed 2026-08-28T04:06:57.698140+00:00)

## What it is
A curated collection of popular and reproducible single-image denoising algorithms, spanning classical filtering, sparse coding, and deep learning methods. It links to code, papers, and web resources for state-of-the-art denoising works.

## Use cases
- find state-of-the-art image denoising algorithms with code
- benchmark denoising methods on AWGN noise
- survey deep learning approaches to image denoising
- compare classical filters like BM3D and NLM with CNN denoisers
- find reproducible implementations for image restoration research
- locate papers and code for noise reduction in images

## When to choose
- you need a curated index of denoising papers with available code
- you are researching or benchmarking image denoising methods
- you want both classical and deep-learning denoising approaches in one place

## When to avoid
- you need a ready-to-use denoising library or application rather than a list of links
- you need video or hyperspectral denoising resources (separate collections exist)
- you expect maintained, runnable code within this repository itself

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: image-processing, benchmarking, machine-learning
- domain: computer-vision, image-processing, machine-learning, awesome-lists
- platform: cross-platform
- tags: image-denoising, curated-list, reproducible-research, image-restoration, deep-learning, benchmark

## Member repositories
- wenbihan/reproducible-image-denoising-state-of-the-art (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.698140+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 2026-08-30T02:26:09.937709+00:00, confidence not recorded.
  - readme: https://github.com/wenbihan/reproducible-image-denoising-state-of-the-art (fetched 2026-08-28T04:06:57.698140+00:00, sha f4c6b4aa60e4)
- Data as of 2026-08-30T08:39:29.467469+00:00.