A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement

Ying, Zhenqiang; Li, Ge; Gao, Wen

doi:10.48550/arxiv.1711.00591

Cited by 70 publications

(144 citation statements)

References 35 publications

Supporting

Mentioning

144

Contrasting

Order By: Relevance

“…Concerning the brightness and contrast enhancement, Ying et al [42] proposed an algorithm, named BIMEF, that involves the use of an image fusion technique similar to high dynamic range, and comparable to the post-processing happening in our brain. Inspired by the human visual system, they design a multi-exposure fusion framework for low-light image enhancement, by proposing a dual-exposure fusion algorithm to provide an accurate contrast and lightness enhancement.…”

Section: Proposed Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

A Development of a New Image Analysis Technique for Detecting the Flame Front Evolution in Spark Ignition Engine under Lean Condition

et al. 2022

View full text Add to dashboard Cite

The aim of herein work is to develop an automatized algorithm for detecting, as objectively as possible, the flame front evolution of lean/ultra-lean mixtures ignited by low temperature plasma-based ignition systems. The low luminosity characterizing the latter conditions makes both kernel formation and combustion development difficult to detect accurately. Therefore, to estimate the igniter capability to efficiently ignite the mixture, ever more performing tools are required. The present work proposes a new image analysis technique, based on a dual-exposure fusion algorithm and on Convolutional Neural Networks (CNNs), to process low brightness images captured via high-speed camera on an optical engine. The performance of the proposed algorithm (PA) is compared to the one of a base reference (BR) algorithm used by the same research group for the imaging analysis. The comparison shows the capability of PA to quantify the flame radius of consecutive combustion cycles with lower dispersion if compared to BR and to correctly detect some events considered as misfires or anomalies by BR. Moreover, the proposed method shows greater capability to detect, in advance, the kernel formation with respect to BR, thus allowing a more detailed analysis of the performance of the igniters. A metric quantitative analysis is carried out, as well, to confirm the above-mentioned results. Therefore, PA results to be more suitable for analyzing ultra-lean combustions, heavily investigated to meet the increasingly stringent legislation on the internal combustion engines. Finally, the proposed algorithm allows us to automatically estimate the flame front evolution, regardless of the user’s interpretation of the phenomenon.

show abstract

Section: Proposed Algorithmmentioning

confidence: 99%

“…Based on these considerations, the algorithm of Ying et al [42] is employed in the present work for enhancing the luminosity of our low-brightness images.…”

Section: Proposed Algorithmmentioning

confidence: 99%

A Development of a New Image Analysis Technique for Detecting the Flame Front Evolution in Spark Ignition Engine under Lean Condition

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The results generated by our methods are with less noise and better color saturation. (Ying, Li, and Gao 2017) 15.95 0.6386 0.4573 DeepUPE (Wang et al 2019a) 13.19 0.4902 0.4634 JED (Ren et al 2018) 16.73 0.6817 0.3899 LIME (Guo, Li, and Ling 2016) 14.07 0.5274 0.4021 SICE (Cai, Gu, and Zhang 2018) 18.06 0.7094 0.5078 LLNet (Lore et al 2017) 17.57 0.7388 0.4021 SRIE (Fu et al 2016) 13.66 0.5509 0.4577 KinD (Zhang et al 2019) 18.42 0.7658 0.2879 KinD++ (Zhang et al 2021) 17.63 0.7994 0.2257 Zero-DCE (Guo et al 2020) 21.12 0.7705 0.2480 EnlightenGAN (Jiang et al 2021) 20.43 0.7921 0.2416 LLFlow (Ours)…”

Section: Evaluation On Ve-lolmentioning

confidence: 99%

Low-Light Image Enhancement with Normalizing Flow

Wang¹,

Wan²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the mapping relationship between them is one-to-many. Previous works based on the pixel-wise reconstruction losses and deterministic processes fail to capture the complex conditional distribution of normally exposed images, which results in improper brightness, residual noise, and artifacts. In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distribu-

show abstract

“…SRIE [36] is a weighted variational model to estimate reflectance and illumination. BIMEF [37] provides a bio-inspired dual-exposure fusion algorithm to provide accurate contrast and lightness enhancement, which obtains results with less contrast and lightness distortion. LIME [15] estimates a structure-aware illumination map with structure prior and uses BM3D [24] for the post-processing denoising operation.…”

Section: Related Workmentioning

confidence: 99%

“…Higher values of PSNR, SSIM, FSIM, UQI, SRER and SAM and lower value of LPIPS and RMSE indicate better (c) BIMEF [37] (d) LIME [15] (e) Dong [38] (f) SRIE [36] (g) MF [35] (h) NPE [34] (i) RRM [21] (j) MBLLEN [20] (k) RetinexNet [16] (l) GLAD [1] (m) EnlightenGan [17] (n) Zero-DCE [19] (o) DA-DRN (p) Ground-Truth Fig. 13.…”

Section: Quantitative Performance Analysismentioning

confidence: 99%

DA-DRN: Degradation-Aware Deep Retinex Network for Low-Light Image Enhancement

Wei¹,

Zhang²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Images obtained in real-world low-light conditions are not only low in brightness, but they also suffer from many other types of degradation, such as color distortion, unknown noise, detail loss and halo artifacts. In this paper, we propose a Degradation-Aware Deep Retinex Network (denoted as DA-DRN) for low-light image enhancement and tackle the above degradation. Based on Retinex Theory, the decomposition net in our model can decompose low-light images into reflectance and illumination maps and deal with the degradation in the reflectance during the decomposition phase directly. We propose a Degradation-Aware Module (DA Module) which can guide the training process of the decomposer and enable the decomposer to be a restorer during the training phase without additional computational cost in the test phase. DA Module can achieve the purpose of noise removal while preserving detail information into the illumination map as well as tackle color distortion and halo artifacts. We introduce Perceptual Loss to train the enhancement network to generate the brightness-improved illumination maps which are more consistent with human visual perception. We train and evaluate the performance of our proposed model over the LOL real-world and LOL synthetic datasets, and we also test our model over several other frequently used datasets without Ground-Truth (LIME, DICM, MEF and NPE datasets). We conduct extensive experiments to demonstrate that our approach achieves a promising effect with good rubustness and generalization and outperforms many other state-of-the-art methods qualitatively and quantitatively. Our method only takes 7 ms to process an image with 600x400 resolution on a TITAN Xp GPU.

show abstract

A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement

Cited by 70 publications

References 35 publications

A Development of a New Image Analysis Technique for Detecting the Flame Front Evolution in Spark Ignition Engine under Lean Condition

A Development of a New Image Analysis Technique for Detecting the Flame Front Evolution in Spark Ignition Engine under Lean Condition

Low-Light Image Enhancement with Normalizing Flow

DA-DRN: Degradation-Aware Deep Retinex Network for Low-Light Image Enhancement

Contact Info

Product

Resources

About