LujiaJin/One-Pot_Multi-Frame_Denoising

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1094 stars · 70 forks observed · 2026-08-28

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

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

library · maturity stable

machine-learning image-processing computer-vision deep-learning computer-vision image-processing machine-learning deep-learning python image-denoising unsupervised-learning noise2noise pytorch research-code bmvc-2022 ijcv linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="LujiaJin/One-Pot_Multi-Frame_Denoising")