From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement
Authors:
Top Cited Papers
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3060-3069
Abstract
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. A deep recursive band network (DRBN) is proposed to recover a linear band representation of an enhanced normal-light image with paired low/normal-light images, and then obtain an improved one by recomposing the given bands via another learnable linear transformation based on a perceptual quality-driven adversarial learning with unpaired data. The architecture is powerful and flexible to have the merit of training with both paired and unpaired data. On one hand, the proposed network is well designed to extract a series of coarse-to-fine band representations, whose estimations are mutually beneficial in a recursive process. On the other hand, the extracted band representation of the enhanced image in the first stage of DRBN (recursive band learning) bridges the gap between the restoration knowledge of paired data and the perceptual quality preference to real high-quality images. Its second stage (band recomposition) learns to recompose the band representation towards fitting perceptual properties of high-quality images via adversarial learning. With the help of this two-stage design, our approach generates enhanced results with well-reconstructed details and visually promising contrast and color distributions. Qualitative and quantitative evaluations demonstrate the superiority of our DRBN.Keywords
This publication has 27 references indexed in Scilit:
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- A fusion-based enhancing method for weakly illuminated imagesSignal Processing, 2016
- A low-light image enhancement method for both denoising and contrast enlarging2015
- Contrast Enhancement Based on Layered Difference Representation of 2D HistogramsIEEE Transactions on Image Processing, 2013
- AVA: A large-scale database for aesthetic visual analysis2012
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Contrast-limited adaptive histogram equalization: speed and effectiveness2002
- A multiscale retinex for bridging the gap between color images and the human observation of scenesIEEE Transactions on Image Processing, 1997
- Properties and performance of a center/surround retinexIEEE Transactions on Image Processing, 1997
- The Retinex Theory of Color VisionScientific American, 1977