Published on Sat Jun 27 2020

A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images

Harshana Weligampola, Gihan Jayatilaka, Suren Sritharan, Roshan Godaliyadda, Parakrama Ekanayaka, Roshan Ragel, Vijitha Herath

Low light image enhancement is an important challenge for the development of computer vision algorithms. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.

0
0
0
Abstract

Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.

Mon Jun 17 2019
Computer Vision
EnlightenGAN: Deep Light Enhancement without Paired Supervision
Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? We propose a highly effective unsupervised generative generative adversarial network, dubbed EnlightenGAN.
0
0
0
Tue Nov 07 2017
Computer Vision
MSR-net:Low-light Image Enhancement Using Deep Convolutional Network
Images captured in low-light conditions usually suffer from very low contrast. Low-light image enhancement is regarded as a machine learning problem. In this model most of the parameters are optimized by back-propagation.
0
0
0
Sun May 31 2020
Computer Vision
Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs
This paper proposes a new light-weight convolutional neural network for non-uniform illumination image enhancement. The model can enhance 0.5 mega-pixel images in real time (50 fps), which is faster than existing methods.
0
0
0
Fri May 04 2018
Computer Vision
Learning to See in the Dark
Short-exposure images suffer from noise, while long exposure can induce blur. Using the presented dataset, we develop a pipeline for processing low-light images. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline.
1
0
1
Mon Jun 28 2021
Computer Vision
R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
Images captured in weak illumination conditions will seriously degrade the image quality. Solving a series of degradation of low-light images can improve the visual quality of the image and the performance of high-level visual tasks.
2
0
0
Mon Dec 07 2020
Computer Vision
CEL-Net: Continuous Exposure for Extreme Low-Light Imaging
Deep learning methods for enhancing dark images learn a mapping from input images to output images with pre-determined discrete exposure levels. We introduce a dataset of 1500 raw images captured in both outdoor and indoor scenes with five different exposure levels and various camera parameters. We develop a model for extreme low-
0
0
0