# LujiaJin/One-Pot_Multi-Frame_Denoising

The official implementation of IJCV & BMVC 2022 paper "One-Pot Multi-frame Denoising".

Repository: https://github.com/LujiaJin/One-Pot_Multi-Frame_Denoising
Canonical: https://ross.abutalabs.com/products/one-pot_multi-frame_denoising
Homepage: https://link.springer.com/article/10.1007/s11263-023-01887-7
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: image-denoising, unsupervised-learning
Last push: 2026-03-02T11:00:27+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 35, longevity 82
- inputs: {"age_days": 1155, "days_push": 184, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1094, forks 70 (observed 2026-08-28T04:03:33.819704+00:00)

## What it is
Official PyTorch implementation of the One-Pot Multi-frame Denoising (OPD) method published at BMVC 2022 and extended in IJCV. It provides unsupervised image denoising training strategies (OPD-RC and OPD-AL) that use mutual supervision among multiple noisy frames without requiring clean labels.

## Use cases
- denoise images without clean training labels
- train an unsupervised denoising model from multiple noisy frames
- remove additive white Gaussian noise from photos
- handle Poisson or Bernoulli noise in images
- perform mixed-blind denoising
- remove random-valued impulse noise or text from images
- reproduce BMVC 2022 denoising paper results

## When to choose
- you have multiple noisy frames of the same scene but no clean ground truth
- you need an unsupervised alternative to Noise2Clean or Noise2Noise
- you want to reproduce or build on the OPD research method

## When to avoid
- you only have a single noisy image per scene
- you need a production-ready plug-and-play denoising application rather than research code
- you require a permissive license since the code is GPL-3.0

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, image-processing, computer-vision, deep-learning
- domain: computer-vision, image-processing, machine-learning, deep-learning
- platform: python
- tags: image-denoising, unsupervised-learning, noise2noise, pytorch, research-code, bmvc-2022, ijcv, linux, gpu

## Member repositories
- LujiaJin/One-Pot_Multi-Frame_Denoising (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:33.819704+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 2026-08-30T06:47:27.015009+00:00, confidence not recorded.
  - readme: https://github.com/LujiaJin/One-Pot_Multi-Frame_Denoising (fetched 2026-08-28T04:03:33.819704+00:00, sha 6f8f4c360f3c)
- Data as of 2026-08-30T08:39:29.467469+00:00.