Low-Light Image Enhancement Using the Cell Vibration Model

Lei, Xiaozhou; Fei, Zixiang; Zhou, Wenju; Zhou, Huiyu; Fei, Minrui

doi:10.1109/tmm.2022.3175634

Cited by 7 publications

(8 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the results of the proposed IAGC with a rich collection of SOTA methods to make comprehensive quantitative comparisons. For qualitative comparison, we select some very recent or robust methods to visually show their performance, including SNR [43], URetinex-Net [41], DeepLPF [29], SCI [28], LIME [8], MF [5], NPE [36], SRIE [6], SDD [10], CDEF [19], LPNet [22], DRBN [46], KinD [51], RUAS [26], FIDE [42], EG [13], MS-RDN [47], Retinex-Net [40], MIRNet [48]. Moreover, following [43] another two classical architecture IPT [3] and Uformer [39] are also selected to make more extensive comparisons.…”

Section: Comparison With Current Methodsmentioning

confidence: 99%

Low illumination image enhancement technology based on iterative dense residual network

Wang

Piao

Wang

et al. 2021

2021 International Conference on Electronic Information Engineering and Computer Science (EIECS)

View full text Add to dashboard Cite

This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark areas, directly learning deep representations from low-light images is insensitive to recovering normal illumination. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks, which enables the correction factor gamma to be learned in a coarse to elaborate manner via adaptively perceiving the deviated illumination. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction, accelerating the training and inference speed. Dark areas usually occupy large scales in low-light images, common local modelling structures, e.g., CNN, SwinIR, are thus insufficient to recover accurate illumination across whole low-light images. We propose a novel Transformer block to completely simulate the dependencies of all pixels across images via a local-to-global hierarchical attention mechanism, so that dark areas could be inferred by borrowing the information from far informative regions in a highly effective manner. Extensive experiments on several benchmark datasets demonstrate that our approach outperforms state-of-the-art methods.

show abstract

Section: Comparison With Current Methodsmentioning

confidence: 99%

Low illumination image enhancement technology based on iterative dense residual network

Wang

Piao

Wang

et al. 2021

2021 International Conference on Electronic Information Engineering and Computer Science (EIECS)

View full text Add to dashboard Cite

show abstract

“…Dong et al [25] exploited a DCP-based method to improve the brightness of low-light videos. Lei et al [29] proposed a simple yet effective low-light image enhancement method to perceive unknown information from dark areas. However, traditional methods cannot effectively extract enhanced details and encounter challenges related to low contrast and unnatural colors.…”

Section: Related Workmentioning

confidence: 99%

“…Three low-light sand-dust images with different scenes, sizes, and degrees of influence of low light and sand dust are selected to demonstrate the effectiveness of the proposed frame quality improvement method. Eight state-of-the-art algorithms are used for comparison: [10], [12], [13], [15], [20], [28], [29], and [33].…”

Section: A Qualitative Evaluationmentioning

confidence: 99%

“…14 and 15 show that the images processed using the methods of (b) Li et al [10], (d) Salazar et al [13], (e) Cai et al [15], and (i) He et al [33] are dark and contain sanddust effects. The algorithms of (f) Li et al [20] and (h) Lei et al [29] can improve the image brightness, but they cannot remove sand-dust. The methods of (c) Yang et al [12] and (g) Ni et al [28] can remove sand-dust; however, the contrast of the image processed by the method of (c) Yang et al [12] is lower than the proposed method.…”

Section: A Qualitative Evaluationmentioning

confidence: 99%

“…Moreover, the illumination is extremely weak, the visibility is reduced, and the scene details are hidden, resulting in the failure of the currently used priors and assumptions, such as the color attenuation [22] and dark channel priors [23]. Although various effective methods for low-light image enhancement have been developed [20], [24]- [27], [29], sanddust removal and brightening are treated separately in lowlight image processing. Consequently, the ambient illumination is dim in images treated for sand-dust removal, and sand dust remains in images treated for low light.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Online Low-Light Sand-Dust Video Enhancement Using Adaptive Dynamic Brightness Correction and a Rolling Guidance Filter

Jia

Yang

et al. 2024

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Sand-dust videos obtained in a low-light environment are characterized by low contrast, nonuniform illumination, color cast, and considerable noise. To realize sand-dust removal and brightness enhancement simultaneously, this paper proposes an online low-light sand-dust video enhancement method using adaptive dynamic brightness correction and a rolling guidance filter. The proposed dual-threshold interframe detection strategy involves two methods to treat low-light sand-dust video frames. The first method involves two components: an adaptive dynamic brightness correction algorithm to correct the color deviation of the low-light video frame and improve its brightness and a rolling guidance filter combined with guided image filtering to enhance the frame details. The second method enhances the quality of the incoming frame by reducing the amount of calculation. The first frame of the video is processed using the first method. The processing method of each subsequent frame is determined according to its interframe detection value with the buffer frame. Through qualitative and quantitative comprehensive experiments on low-light sand-dust images and videos, the performance of the proposed method is compared with those of state-of-the-art methods. The proposed method for frame quality improvement achieves the best visual effect in enhancing the quality of low-light sand-dust images, as indicated by the best objective evaluation indicators. Moreover, compared with the framewise enhancement method, the video processing efficiency associated with the dualthreshold interframe detection strategy is 2.77 times higher.

show abstract

Low-light image enhancement based on cell vibration energy model and lightness difference

Lei,

Fei,

Zhou

et al. 2024

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Low-Light Image Enhancement Using the Cell Vibration Model

Cited by 7 publications

References 55 publications

Low illumination image enhancement technology based on iterative dense residual network

Low illumination image enhancement technology based on iterative dense residual network

Online Low-Light Sand-Dust Video Enhancement Using Adaptive Dynamic Brightness Correction and a Rolling Guidance Filter

Low-light image enhancement based on cell vibration energy model and lightness difference

Contact Info

Product

Resources

About