# google-research/maxim

[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.

Repository: https://github.com/google-research/maxim
Canonical: https://ross.abutalabs.com/products/maxim
Homepage: https://arxiv.org/abs/2201.02973
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image, architecture, image-processing, computer-vision, transformer, mlp, enhancement, image-restoration, restoration, denoising, deblurring, dehazing, deraining, retouching, low-level-vision, image-enhancement
Archived: true
Last push: 2023-06-09T18:15:50+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1632, "days_push": 1181, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1085, forks 116 (observed 2026-08-28T04:03:31.633255+00:00)

## What it is
Official implementation of MAXIM, a multi-axis MLP architecture for low-level image processing tasks, presented as a CVPR 2022 oral paper. It provides pretrained models and training code achieving state-of-the-art results on denoising, deblurring, deraining, dehazing, and image enhancement benchmarks.

## Use cases
- remove noise from photos with a deep learning model
- deblur blurry images
- remove rain streaks from images
- dehaze foggy photos
- enhance low-light images
- retouch photos automatically
- research a UNet-style MLP vision backbone

## When to avoid
- you need a production image editing app with a UI
- you want actively maintained code with frequent updates
- your task is high-level vision like classification or detection

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning
- platform: python
- tags: image-restoration, denoising, deblurring, deraining, dehazing, low-light-enhancement, mlp-architecture, cvpr-2022, research-code, gpu

## Member repositories
- google-research/maxim (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.633255+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 2026-08-30T06:49:48.572391+00:00, confidence not recorded.
  - readme: https://github.com/google-research/maxim (fetched 2026-08-28T04:03:31.633255+00:00, sha b26cbdb9a8e5)
  - homepage: https://arxiv.org/abs/2201.02973 (fetched 2026-08-29T12:52:52.697004+00:00, sha b44601909bcc)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:52:52.706560+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:52:52.710723+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:52:52.712718+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:52:52.708622+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.