HINet: Half Instance Normalization Network for Image Restoration

Last update: Dec 31, 2022

Related tags

Deep Learning HINet

Overview

HINet: Half Instance Normalization Network for Image Restoration

Liangyu Chen, Xin Lu, Jie Zhang, Xiaojie Chu, Chengpeng Chen

Paper: https://arxiv.org/abs/2105.06086

In this paper, we explore the role of Instance Normalization in low-level vision tasks. Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks. Based on HIN Block, we design a simple and powerful multi-stage network named HINet, which consists of two subnetworks. With the help of HIN Block, HINet surpasses the state-of-the-art (SOTA) on various image restoration tasks. For image denoising, we exceed it 0.11dB and 0.28 dB in PSNR on SIDD dataset, with only 7.5% and 30% of its multiplier-accumulator operations (MACs), 6.8 times and 2.9 times speedup respectively. For image deblurring, we get comparable performance with 22.5% of its MACs and 3.3 times speedup on REDS and GoPro datasets. For image deraining, we exceed it by 0.3 dB in PSNR on the average result of multiple datasets with 1.4 times speedup. With HINet, we won 1st place on the NTIRE 2021 Image Deblurring Challenge - Track2. JPEG Artifacts, with a PSNR of 29.70.

Network Architecture

Installation

This implementation based on BasicSR which is a open source toolbox for image/video restoration tasks.

python 3.6.9
pytorch 1.5.1
cuda 10.1

git clone https://github.com/megvii-model/HINet
cd HINet
pip install -r requirements.txt
python setup.py develop --no_cuda_ext

Image Restoration Tasks

Image denoise, deblur, derain.

Image Denoise - SIDD dataset (Coming soon)

Image Deblur - GoPro dataset (Click to expand)

prepare data
- mkdir ./datasets/GoPro
- download the train set in ./datasets/GoPro/train and test set in ./datasets/GoPro/test (refer to MPRNet)
- it should be like:
```
./datasets/
./datasets/GoPro/
./datasets/GoPro/train/
./datasets/GoPro/train/input/
./datasets/GoPro/train/target/
./datasets/GoPro/test/
./datasets/GoPro/test/input/
./datasets/GoPro/test/target/
```
- python scripts/data_preparation/gopro.py
  - crop the train image pairs to 512x512 patches.
eval
- download pretrained model to ./experiments/pretrained_models/HINet-GoPro.pth
- python basicsr/test.py -opt options/test/REDS/HINet-GoPro.yml
train
- python -m torch.distributed.launch --nproc_per_node=8 --master_port=4321 basicsr/train.py -opt options/train/GoPro/HINet.yml --launcher pytorch

Image Deblur - REDS dataset (Click to expand)

prepare data
- mkdir ./datasets/REDS
- download the train / val set from train_blur, train_sharp, val_blur, val_sharp to ./datasets/REDS/ and unzip them.
- it should be like
```
./datasets/
./datasets/REDS/
./datasets/REDS/val/
./datasets/REDS/val/val_blur_jpeg/
./datasets/REDS/val/val_sharp/
./datasets/REDS/train/
./datasets/REDS/train/train_blur_jpeg/
./datasets/REDS/train/train_sharp/
```
- python scripts/data_preparation/reds.py
  - flatten the folders and extract 300 validation images.
eval
- download pretrained model to ./experiments/pretrained_models/HINet-REDS.pth
- python basicsr/test.py -opt options/test/REDS/HINet-REDS.yml
train
- python -m torch.distributed.launch --nproc_per_node=8 --master_port=4321 basicsr/train.py -opt options/train/REDS/HINet.yml --launcher pytorch

Image Derain - Rain13k dataset (Click to expand)

prepare data

mkdir ./datasets/Rain13k
download the train set and test set (refer to MPRNet)

it should be like

./datasets/
./datasets/Rain13k/
./datasets/Rain13k/train/
./datasets/Rain13k/train/input/
./datasets/Rain13k/train/target/
./datasets/Rain13k/test/
./datasets/Rain13k/test/Test100/
./datasets/Rain13k/test/Rain100H/
./datasets/Rain13k/test/Rain100L/
./datasets/Rain13k/test/Test2800/
./datasets/Rain13k/test/Test1200/

eval
- download pretrained model to ./experiments/pretrained_models/HINet-Rain13k.pth
- For Test100:
  - python basicsr/test.py -opt options/test/Rain13k/HINet-Test100.yml
- For Rain100H
  - python basicsr/test.py -opt options/test/Rain13k/HINet-Rain100H.yml
- For Rain100L
  - python basicsr/test.py -opt options/test/Rain13k/HINet-Rain100L.yml
- For Test2800
  - python basicsr/test.py -opt options/test/Rain13k/HINet-Test2800.yml
- For Test1200
  - python basicsr/test.py -opt options/test/Rain13k/HINet-Test1200.yml
train
- python -m torch.distributed.launch --nproc_per_node=8 --master_port=4321 basicsr/train_rain.py -opt options/train/Rain13k/HINet.yml --launcher pytorch

Results

Some of the following results are higher than the original paper as we optimized some hyper-parameters.

Citations

If HINet helps your research or work, please consider citing HINet.

@inproceedings{chen2021hinet,
  title={HINet: Half Instance Normalization Network for Image Restoration},
  author={Liangyu Chen and Xin Lu and Jie Zhang and Xiaojie Chu and Chengpeng Chen},
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year={2021}
}

Contact

If you have any questions, please contact [email protected] or [email protected] .

HINet: Half Instance Normalization Network for Image Restoration

Related tags

Overview

HINet: Half Instance Normalization Network for Image Restoration

Liangyu Chen, Xin Lu, Jie Zhang, Xiaojie Chu, Chengpeng Chen

Paper: https://arxiv.org/abs/2105.06086

Network Architecture

Installation

Image Restoration Tasks

Results

Citations

Contact

Owner

Hyperbolic Hierarchical Clustering.

PyTorch code for our ECCV 2020 paper "Single Image Super-Resolution via a Holistic Attention Network"

Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures

The world's simplest facial recognition api for Python and the command line

GNN-based Recommendation Benchma

Implementation of the CVPR 2021 paper "Online Multiple Object Tracking with Cross-Task Synergy"

Calculates carbon footprint based on fuel mix and discharge profile at the utility selected. Can create graphs and tabular output for fuel mix based on input file of series of power drawn over a period of time.

ParaGen is a PyTorch deep learning framework for parallel sequence generation

Official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels".

The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

Implementation of character based convolutional neural network

ML powered analytics engine for outlier detection and root cause analysis.

The Simplest DCGAN Implementation

The dataset of tweets pulling from Twitters with keyword: Hydroxychloroquine, location: US, Time: 2020

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

Definition of a business problem according to Wilson Lower Bound Score and Time Based Average Rating

[SIGGRAPH Asia 2021] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN

Offical code for the paper: "Growing 3D Artefacts and Functional Machines with Neural Cellular Automata" https://arxiv.org/abs/2103.08737

The code for the NeurIPS 2021 paper "A Unified View of cGANs with and without Classifiers".

Extract MNIST handwritten digits dataset binary file into bmp images