# csguoh/MambaIR

[ECCV2024, CVPR2025] MambaIR and MambaIRv2!

Repository: https://github.com/csguoh/MambaIR
Canonical: https://ross.abutalabs.com/products/mambair
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-06-03T02:29:44+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 85, release rhythm 8, longevity 66
- inputs: {"age_days": 924, "days_push": 92, "days_rel": 637, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1171, forks 96 (observed 2026-08-28T04:03:51.544170+00:00)

## What it is
MambaIR and MambaIRv2 are PyTorch-based image restoration models built on Mamba state-space models, published at ECCV 2024 and CVPR 2025. They provide attentive state-space backbones for tasks like super-resolution, denoising, and deblurring with pretrained weights on HuggingFace.

## Use cases
- restore degraded images with a mamba-based model
- perform image super-resolution
- denoise photos with a state space model
- deblur images using deep learning
- reproduce ECCV/CVPR image restoration baselines
- compare restoration models on PSNR benchmarks

## When to choose
- you need efficient global-context image restoration models
- you want state-of-the-art super-resolution or denoising baselines
- you are researching state-space models for low-level vision

## When to avoid
- you need a production-ready image editing application
- you work outside image restoration tasks
- you lack a GPU for training or inference

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python
- tags: image-restoration, state-space-models, mamba, super-resolution, denoising, deblurring, eccv2024, cvpr2025, research-code, gpu

## Member repositories
- csguoh/MambaIR (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:51.544170+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 2026-08-30T06:28:30.909257+00:00, confidence not recorded.
  - readme: https://github.com/csguoh/MambaIR (fetched 2026-08-28T04:03:51.544170+00:00, sha bea18f7cc4b9)
- Data as of 2026-08-30T08:39:29.467469+00:00.