MAXIM: Multi-Axis MLP for Image Processing (CVPR 2022 Oral, Best Paper Nomination)
This repo hosts the official implementation of the MAXIM models:
"MAXIM: Multi-Axis MLP for Image Processing". CVPR 2022 Oral.
Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, and Yinxiao Li
Google Research, University of Texas at Austin
Disclaimer: This is not an officially supported Google product.
News:
- Oct 21, 2022: MAXIM models have been ported to TensorFlow by @sayakpaul. Check it out here: maxim-tf. He also created a couple of Hugging Face Spaces to allow users to quickly try out the different models:
- Sep 8, 2022: our Google AI blog covering both MaxViT and MAXIM is live.
- Apr 25, 2022: Added demos.
- Colab demo by @deshwalmahesh
- Replicate web demo
.
- Colab demo by @deshwalmahesh
- Jun 22, 2022: MAXIM selected as 1 of the best paper nomination!
- Mar 29, 2022: MAXIM selected for an oral presentation at CVPR 2022!
- Mar 28, 2022: initial push to Github.
- Mar 3, 2022: paper accepted to CVPR 2022!
- Jan 9, 2022: initial uploads to Arxiv
Quick Demos
Try the web demo for Image Denoising, Deblurring, Deraining, Dehazing and Enhancement with customized input image here
Architecture
Installation
Install dependencies:
pip install -r requirements.txt
Setup project:
pip install .
Results and Pre-trained models
We provide the pre-trained models and visual results. Please contact us if you have any questions or requests.
Task | Dataset | PSNR | SSIM | Model | #params | FLOPs | ckpt | outputs |
---|---|---|---|---|---|---|---|---|
Denoising | SIDD | 39.96 | 0.960 | MAXIM-3S | 22.2M | 339G | ckpt | images |
Denoising | DND | 39.84 | 0.954 | MAXIM-3S | 22.2M | 339G | ckpt | images |
Deblurring | GoPro | 32.86 | 0.961 | MAXIM-3S | 22.2M | 339G | ckpt | images |
Deblurring | HIDE | 32.83 | 0.956 | MAXIM-3S | 22.2M | 339G | ckpt | images |
Deblurring | REDS | 28.93 | 0.865 | MAXIM-3S | 22.2M | 339G | ckpt | images |
Deblurring | RealBlur-R | 39.45 | 0.962 | MAXIM-3S | 22.2M | 339G | ckpt | images |
Deblurring | RealBlur-J | 32.84 | 0.935 | MAXIM-3S | 22.2M | 339G | ckpt | images |
Deraining | Rain13k | 33.24 | 0.933 | MAXIM-2S | 14.1M | 216G | ckpt | images |
Deraining | Raindrop | 31.87 | 0.935 | MAXIM-2S | 14.1M | 216G | ckpt | images |
Dehazing | RESIDE-Indoor | 38.11 | 0.991 | MAXIM-2S | 14.1M | 216G | ckpt | images |
Dehazing | RESIDE-Outdoor | 34.19 | 0.985 | MAXIM-2S | 14.1M | 216G | ckpt | images |
Enhancement | LOL | 23.43 | 0.863 | MAXIM-2S | 14.1M | 216G | ckpt | images |
Enhancement | FiveK | 26.15 | 0.945 | MAXIM-2S | 14.1M | 216G | ckpt | images |
Demo
First download corresponding checkpoints and then go ahead and run:
Image Denoising (click to expand)
python3 maxim/run_eval.py --task Denoising --ckpt_path ${SIDD_CKPT_PATH} \
--input_dir maxim/images/Denoising --output_dir maxim/images/Results --has_target=False
Image Deblurring (click to expand)
python3 maxim/run_eval.py --task Deblurring --ckpt_path ${GOPRO_CKPT_PATH} \
--input_dir maxim/images/Deblurring --output_dir maxim/images/Results --has_target=False
Image Deraining (click to expand)
Rain streak:
python3 maxim/run_eval.py --task Deraining --ckpt_path ${RAIN13K_CKPT_PATH} \
--input_dir maxim/images/Deraining --output_dir maxim/images/Results --has_target=False
Rain drop:
python3 maxim/run_eval.py --task Deraining --ckpt_path ${RAINDROP_CKPT_PATH} \
--input_dir maxim/images/Deraining --output_dir maxim/images/Results --has_target=False
Image Dehazing (click to expand)
Indoor:
python3 maxim/run_eval.py --task Dehazing --ckpt_path ${REDISE_INDOOR_CKPT_PATH} \
--input_dir maxim/images/Dehazing --output_dir maxim/images/Results --has_target=False
Outdoor:
python3 maxim/run_eval.py --task Dehazing --ckpt_path ${REDISE_OUTDOOR_CKPT_PATH} \
--input_dir maxim/images/Dehazing --output_dir maxim/images/Results --has_target=False
Image Enhancement (click to expand)
Low-light enhancement:
python3 maxim/run_eval.py --task Enhancement --ckpt_path ${LOL_CKPT_PATH} \
--input_dir maxim/images/Enhancement --output_dir maxim/images/Results --has_target=False
Retouching:
python3 maxim/run_eval.py --task Enhancement --ckpt_path ${FIVEK_CKPT_PATH} \
--input_dir maxim/images/Enhancement --output_dir maxim/images/Results --has_target=False
Results
Citation
Should you find this repository useful, please consider citing:
@article{tu2022maxim,
title={MAXIM: Multi-Axis MLP for Image Processing},
author={Tu, Zhengzhong and Talebi, Hossein and Zhang, Han and Yang, Feng and Milanfar, Peyman and Bovik, Alan and Li, Yinxiao},
journal={CVPR},
year={2022},
}
Acknowledgement
This repository is built on the vision_transformer and musiq repositories. Our work is also inspired by HiT, MPRNet, and HINet.