From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement

By Wenhan Yang, Yuming Fang, Yue Wang, Jiaying Liu. Computer Vision and Pattern Recognition, 2020

530 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f478678516593b296f7e55aecae34a2b059460e6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Learning a Simple Low-Light Image Enhancer from Paired Low-Light Instances (2023, methodology): “PairLIE is compared with 13 state-of-the-art LIE meth-ods, which can be divided into the following three categories: traditional methods (SDD [9], STAR [34]), supervised approaches (MBLLEN [20], RetinexNet [32], GALD-Net [30], KinD [38], DRBN [36], URetinexNet [33]), and unsupervised methods (Zero-D”
Low-Light Image and Video Enhancement Using Deep Learning: A Survey (2021, methodology): “[33] propose a semi-supervised deep recursive band network (DRBN).”
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation (2021, background): “[29] proposed a semi-supervised model for low-light image enhancement, which performs enhancement in two stages.”
LR3M: Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model (2020, unknown): “In [27], Yang et al.”
Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement (2020, methodology): “In addition, dozens of methods also train their networks without paired supervision [40, 12, 8].”
Toward Fast, Flexible, and Robust Low-Light Image Enhancement (2022, unknown): “As for low-light image enhancement, we compared our SCI with four recently-proposed model-based methods (including LECARM [17], SDD [10], STAR [26]), four advanced supervised learning meth-ods (including RetinexNet [3], KinD [34], FIDE [27], DRBN [30]), and four unsupervised learning methods (includ”
Low-Light Image Enhancement with Wavelet-Based Diffusion Models (2023, methodology): “The results presented in rows 1 and 3 show that DRBN, MIRNet, RUAS, and GDP are unable to properly improve the contrast of the images, yielding underexposed or overexposed results.”
SNR-Aware Low-light Image Enhancement (2022, background): “[51] presented a semi-supervised approach to recover a linear-band representation of the low-light image.”