LLE-NET: A Low-Light Image Enhancement Algorithm Based on Curve Estimation
Open Access
- 19 April 2024
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 12 (8) , 1228
Abstract
Low-light image enhancement is very significant for vision tasks. We introduce Low-light Image Enhancement via Deep Learning Network (LLE-NET), which employs a deep network to estimate curve parameters. Cubic curves and gamma correction are employed for enhancing low-light images. Our research trains a lightweight network to estimate the parameters that determine the correction curve. By the results of the deep learning network, accurate correction curves are confirmed, which are used for the per-pixel correction of RGB channels. The image enhanced by our models closely resembles the input image. To further accelerate the inferring speed of the low-light enhancement model, a low-light enhancement model based on gamma correction is proposed with one iteration. LLE-NET exhibits remarkable inference speed, achieving 400 fps on a single GPU for images sized while maintaining pleasing enhancement quality. The enhancement model based on gamma correction attains an impressive inference speed of 800 fps for images sized on a single GPU.
Keywords
Funding Information
- National Natural Science Foundation of China (U1813221)
This publication has 45 references indexed in Scilit:
- Low light image enhancement algorithm based on improved multi-objective grey wolf optimization with detail feature enhancementJournal of King Saud University Computer and Information Sciences, 2023
- Zero-reference deep learning for low-light image enhancement of underground utilities 3D reconstructionAutomation in Construction, 2023
- Underwater image enhancement by modified color correction and adaptive Look-Up-Table with edge-preserving filterSignal Processing: Image Communication, 2023
- Low-light Image Enhancement Algorithm Based on Exposure Prediction and Hybrid Feature Weighted Fusion StrategyJournal of Physics: Conference Series, 2022
- Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation DatasetInternational Journal of Computer Vision, 2021
- Beyond Brightening Low-light ImagesInternational Journal of Computer Vision, 2021
- Multi-scale retinex-based contrast enhancement method for preserving the naturalness of color imageOptical Review, 2020
- Histogram Equalization Variants as Optimization Problems: A ReviewArchives of Computational Methods in Engineering, 2020
- Normalised gamma transformation‐based contrast‐limited adaptive histogram equalisation with colour correction for sand–dust image enhancementIET Image Processing, 2020
- Preserving brightness in histogram equalization based contrast enhancement techniquesDigital Signal Processing, 2004