Learning Lightweight Low-Light Enhancement Network using Pseudo Well-Exposed Images

Related tags

Deep Learning LLKD
Overview

Learning Lightweight Low-Light Enhancement Network using Pseudo Well-Exposed Images

This repository contains the implementation of the following paper:

Learning Lightweight Low-Light Enhancement Network using Pseudo Well-Exposed Images
Seonggwan Ko*, Jinsun Park*, Byungjoo Chae and Donghyeon Cho
Signal Processing Letters

Overview

Visual results

Requirements

The following packages must be installed to perform the proposed model:

  • PyTorch 1.7.1
  • torchvision 0.8.2
  • Pillow 8.2.0
  • TensorBoardX 2.2
  • tqdm

Test

Test datasets should be arranged as the following folder dataset/test.

dataset
│   ├── test
│   │   ├── LIME
│   │   ├── LOL
│   │   ├── DICM
│   │   └── ...
└── ...

If you set up the folder, you can make it run.

python test.py

Train

To train the proposed model, the following options are required:

python train.py --lowlight_images_path 'your_dataset_path' --gt_images_path 'your_GT_dataset_path' --pretrain_dir  'your_pretrain_path'

lowlight_images_path is the path of your low-light image

gt_images_path is the path of your ground-truth image

pretrain_dir is the path of your pretrained teacher model path

Dataset

We provide 10,000 training pairs and 387 test images.

Please click here if you want to download our dataset.

Dataset Creation

  • We collected 25,967 low-light images from BDD100k(4,830 images) and Dark Zurich(5,336 images), LoLi-Phone(6,442 images), ExDark(7,263 images), SICE(1,611), LOL(485 images).
  • Then, we generate pseudo well-exposed images using the pretrained EnlightenGAN, and additionally reduce noise using DnCNN.

Citation

 @ARTICLE{,
  author={S. {Ko} and J. {Park} and B. {Chae} and D. {Cho}},
  journal={IEEE Signal Processing Letters}, 
  title={Learning Lightweight Low-Light Enhancement Network using Pseudo Well-Exposed Images}, 
  year={2021}
}

License and Acknowledgement

The code framework is mainly modified from Zero-DCE, AdaBelief and SPKD. Please refer to the original repo for more usage and documents. Thanks to authors for sharing the codes!

You might also like...
A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering.

DeepFilterNet A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering. libDF contains Rust code used for dat

Hendrik Schröter 292 Dec 25, 2022
python-timbl, originally developed by Sander Canisius, is a Python extension module wrapping the full TiMBL C++ programming interface. With this module, all functionality exposed through the C++ interface is also available to Python scripts. Being able to access the API from Python greatly facilitates prototyping TiMBL-based applications.

README: python-timbl Authors: Sander Canisius, Maarten van Gompel Contact: [email protected] Web site: https://github.com/proycon/python-timbl/ pytho

Maarten van Gompel 16 Jan 16, 2022
PyKale is a PyTorch library for multimodal learning and transfer learning as well as deep learning and dimensionality reduction on graphs, images, texts, and videos
PyKale is a PyTorch library for multimodal learning and transfer learning as well as deep learning and dimensionality reduction on graphs, images, texts, and videos

PyKale is a PyTorch library for multimodal learning and transfer learning as well as deep learning and dimensionality reduction on graphs, images, texts, and videos. By adopting a unified pipeline-based API design, PyKale enforces standardization and minimalism, via reusing existing resources, reducing repetitions and redundancy, and recycling learning models across areas.

PyKale 370 Dec 27, 2022
Implementation for paper "STAR: A Structure-aware Lightweight Transformer for Real-time Image Enhancement" (ICCV 2021).

STAR-pytorch Implementation for paper "STAR: A Structure-aware Lightweight Transformer for Real-time Image Enhancement" (ICCV 2021). CVF (pdf) STAR-DC

null 43 Dec 21, 2022
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision Project | Arxiv | Abstract It is very challenging for various visual tasks such as image

CVSM Group - email: czhu@bupt.edu.cn 377 Jan 7, 2023
Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter

ACE Please find the preliminary version published at BMVC 2020 in the folder BMVC_version, and its extended journal version in Journal_version. Datase

null 28 Dec 25, 2022
Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

null 567 Dec 26, 2022
Code for BMVC2021
Code for BMVC2021 "MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation"

MOS-Multi-Task-Face-Detect Introduction This repo is the official implementation of "MOS: A Low Latency and Lightweight Framework for Face Detection,

null 104 Dec 8, 2022
Speech Enhancement Generative Adversarial Network Based on Asymmetric AutoEncoder
Speech Enhancement Generative Adversarial Network Based on Asymmetric AutoEncoder

ASEGAN: Speech Enhancement Generative Adversarial Network Based on Asymmetric AutoEncoder 中文版简介 Readme with English Version 介绍 基于SEGAN模型的改进版本，使用自主设计的非

Nitin 53 Nov 17, 2022
Comments
Owner
Seonggwan Ko
Bachelor | Computer Science | Computer Vision & Image Processing |
Seonggwan Ko
GitHub
The code of Zero-shot learning for low-light image enhancement based on dual iteration

Zero-shot-dual-iter-LLE The code of Zero-shot learning for low-light image enhancement based on dual iteration. You can get the real night image tests

null 1 Mar 18, 2022
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

Under-exposure introduces a series of visual degradation, i.e. decreased visibility, intensive noise, and biased color, etc. To address these problems, we propose a novel semi-supervised learning approach for low-light image enhancement.

Yang Wenhan 117 Jan 3, 2023
Tensorflow implementation of MIRNet for Low-light image enhancement

MIRNet Tensorflow implementation of the MIRNet architecture as proposed by Learning Enriched Features for Real Image Restoration and Enhancement. Lanu

Soumik Rakshit 91 Jan 6, 2023
Official implementation for "Low-light Image Enhancement via Breaking Down the Darkness"

Low-light Image Enhancement via Breaking Down the Darkness by Qiming Hu, Xiaojie Guo. 1. Dependencies Python3 PyTorch>=1.0 OpenCV-Python, TensorboardX

Qiming Hu 30 Jan 1, 2023
The code release of paper Low-Light Image Enhancement with Normalizing Flow

[AAAI 2022] Low-Light Image Enhancement with Normalizing Flow Paper | Project Page Low-Light Image Enhancement with Normalizing Flow Yufei Wang, Renji

Yufei Wang 176 Jan 6, 2023
3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021)

3DDUNET This is the code for 3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021) Conference Paper Link Dataset We use SMOID dataset

null 1 Jan 7, 2022
git《Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser》(2021) GitHub: [fig5]

Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser Abstract The success of deep denoisers on real-world colo

Yue Cao 51 Nov 22, 2022
Code for HLA-Face: Joint High-Low Adaptation for Low Light Face Detection (CVPR21)

HLA-Face: Joint High-Low Adaptation for Low Light Face Detection The official PyTorch implementation for HLA-Face: Joint High-Low Adaptation for Low L

Wenjing Wang 77 Dec 8, 2022
EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising

EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising By Tengfei Liang, Yi Jin, Yidong Li, Tao Wang. Th

workingcoder 115 Jan 5, 2023
An image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testingAn image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testing

SVM Données Une base d’images contient 490 images pour l’apprentissage (400 voitures et 90 bateaux), et encore 21 images pour fait des tests. Prétrait

Achraf Rahouti 3 Nov 30, 2021