MSR-net:Low-light Image Enhancement Using Deep Convolutional Network
arXiv:1711.02488
Abstract
Images captured in low-light conditions usually suffer from very low contrast, which increases the difficulty of subsequent computer vision tasks in a great extent. In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed. Firstly, we show that multi-scale Retinex is equivalent to a feedforward convolutional neural network with different Gaussian convolution kernels. Motivated by this fact, we consider a Convolutional Neural Network(MSR-net) that directly learns an end-to-end mapping between dark and bright images. Different fundamentally from existing approaches, low-light image enhancement in this paper is regarded as a machine learning problem. In this model, most of the parameters are optimized by back-propagation, while the parameters of traditional models depend on the artificial setting. Experiments on a number of challenging images reveal the advantages of our method in comparison with other state-of-the-art methods from the qualitative and quantitative perspective.
9pages
References in corpus (1)
Cited by in corpus (27)
- R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
- DeepISP: Towards Learning an End-to-End Image Processing Pipeline
- Towards Low Light Enhancement with RAW Images
- Enabling Pedestrian Safety using Computer Vision Techniques: A Case Study of the 2018 Uber Inc. Self-driving Car Crash
- Learning Enriched Features for Real Image Restoration and Enhancement
- Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
- Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
- Self-supervised Low Light Image Enhancement and Denoising
- Frequency Domain Loss Function for Deep Exposure Correction of Dark Images
- Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement
- A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images
- Semantic Image Completion and Enhancement using Deep Learning
- DALE : Dark Region-Aware Low-light Image Enhancement
- Freeform surface topology prediction for prescribed illumination via semi-supervised learning
- L^2UWE: A Framework for the Efficient Enhancement of Low-Light Underwater Images Using Local Contrast and Multi-Scale Fusion
- Color-wise Attention Network for Low-light Image Enhancement
- Image Correction via Deep Reciprocating HDR Transformation
- Low Light Image Enhancement via Global and Local Context Modeling
- DA-DRN: Degradation-Aware Deep Retinex Network for Low-Light Image Enhancement
- SID-NISM: A Self-supervised Low-light Image Enhancement Framework
- LED2Net: Deep Illumination-aware Dehazing with Low-light and Detail Enhancement
- Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features
- Extreme Low-Light Imaging with Multi-granulation Cooperative Networks
- BLNet: A Fast Deep Learning Framework for Low-Light Image Enhancement with Noise Removal and Color Restoration
- Attention-based network for low-light image enhancement
- Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
- Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References