融合全局-局部特征的低照度图像增强方法

doi:10.3778/j.issn.1002-8331.2404-0207

摘要/Abstract

摘要： 受环境黑暗影响或设备性能限制，所拍摄的图像往往存在低对比度、低亮度、高噪声等问题，从而使图像视觉感知质量差，成像效果不理想。为了解决上述问题，提出了一种融合全局-局部特征的低照度图像增强方法，以恢复正常光照图像。构建特征提取模块初步提取图像的重要特征。设计了一个具有方向性注意力的Transformer准确地提取全局特征并捕获长期依赖关系，在网络结构中加入了残差模块，用于提取局部特征并关注低层次细节。采用信噪比图指导全局和局部特征融合。所提出的增强方法与现有的方法进行定性和定量的比较，并对网络结构进行了消融实验，实验结果表明，该方法能有效解决低照度图像曝光不足、色彩失真、噪声干扰等问题，具有一定的应用价值。

关键词: 低照度图像增强, 特征融合, Transformer, 残差网络

Abstract: Affected by environmental darkness or limited device performance, the captured images often have issues such as low contrast, low brightness, and high noise, resulting in poor visual perception quality and unsatisfactory imaging results. To address the aforementioned issues, a low illumination image enhancement method that integrates global local features is proposed to restore normal illuminated images. Firstly, it constructs a feature extraction module to preliminarily extract important features of the image. Secondly, a Transformer with directional attention is designed to accurately extract global features and capture long-term dependencies. A residual module is added to the network structure to extract local features and focus on low-level details. Finally, a signal-to-noise ratio map is used to guide global and local feature fusion. The proposed enhancement method is qualitatively and quantitatively compared with existing methods, and ablation experiments are conducted on the network structure. The experimental results show that the method can effectively solve problems such as insufficient exposure, color distortion, and noise interference in low light images, and has certain application value.

Key words: low light image enhancement, feature fusion, Transformer, residual network

黄婷婷, 曾上游, 王靖. 融合全局-局部特征的低照度图像增强方法[J]. 计算机工程与应用, 2025, 61(13): 321-328.

HUANG Tingting, ZENG Shangyou, WANG Jing. Low Illumination Image Enhancement Method Integrating Global-Local Features[J]. Computer Engineering and Applications, 2025, 61(13): 321-328.

参考文献

[1] LI H C, XIONG P F, FAN H Q, et al. DFANet: deep feature aggregation for real-time semantic segmentation[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 9514-9523.
[2] LIU W Y, WEN Y D, YU Z D, et al. SphereFace: deep hypersphere embedding for face recognition[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6738-6746.
[3] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788.
[4] ZUIDERVELD K. Contrast limited adaptive histogram equali- zation[J]. Graphics Gems, 1994: 474-485.
[5] LAND E H, MCCANN J J. Lightness and retinex theory[J]. JOSA, 1971, 61(1): 1-11.
[6] IBRAHIM H, KONG N S P. Brightness preserving dynamic histogram equalization for image contrast enhancement[J]. IEEE Transactions on Consumer Electronics, 2007, 53(4): 1752-1758.
[7] WANG C, YE Z F. Brightness preserving histogram equali- zation with maximum entropy: a variational perspective[J]. IEEE Transactions on Consumer Electronics, 2005, 51(4): 1326-1334.
[8] CHEN S D, RAMLI A R. Minimum mean brightness error bi-histogram equalization in contrast enhancement[J]. IEEE Transactions on Consumer Electronics, 2003, 49(4): 1310-1319.
[9] JOBSON D J, RAHMAN Z, WOODELL G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965-976.
[10] WANG S H, ZHENG J, HU H M, et al. Naturalness preserved enhancement algorithm for non-uniform illumination images[J]. IEEE Transactions on Image Processing, 2013, 22(9): 3538-3548.
[11] LI M D, LIU J Y, YANG W H, et al. Structure-revealing low-light image enhancement via robust retinex model[J]. IEEE Transactions on Image Processing, 2018, 27(6): 2828-2841.
[12] WEI C, WANG W J, YANG W H, et al. Deep retinex decomposition for low-light enhancement[J]. arXiv:1808.04560, 2018.
[13] ZHANG Y H, ZHANG J W, GUO X J. Kindling the darkness: a practical low-light image enhancer[C]//Proceedings of the 27th ACM International Conference on Multimedia. New York: ACM, 2019: 1632-1640.
[14] ZHANG Y H, GUO X J, MA J Y, et al. Beyond brightening low-light images[J]. International Journal of Computer Vision, 2021, 129(4): 1013-1037.
[15] WU W H, WENG J, ZHANG P P, et al. URetinex-Net: retinex-based deep unfolding network for low-light image enhancement[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 5891-5900.
[16] HAI J, XUAN Z, YANG R, et al. R2RNet: low-light image enhancement via real-low to real-normal network[J]. Journal of Visual Communication and Image Representation, 2023, 90: 103712.
[17] GUO C L, LI C Y, GUO J C, et al. Zero-reference deep curve estimation for low-light image enhancement[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 1777-1786.
[18] JIANG Y F, GONG X Y, LIU D, et al. EnlightenGAN: deep light enhancement without paired supervision[J]. IEEE Transactions on Image Processing, 2021, 30: 2340-2349.
[19] MA L, MA T Y, LIU R S, et al. Toward fast, flexible, and robust low-light image enhancement[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 5627-5636.
[20] YANG W H, WANG S Q, FANG Y M, et al. From fidelity to perceptual quality: a semi-supervised approach for low-light image enhancement[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 3060-3069.
[21] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017: 5998-6008.
[22] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv:2010.11929, 2020.
[23] CHEN Z, ZHANG Y, GU J, et al. Cross aggregation transformer for image restoration[C]//Advances in Neural Information Processing Systems, 2022: 25478-25490.
[24] WANG T, ZHANG K H, SHEN T R, et al. Ultra-high-definition low-light image enhancement: a benchmark and transformer based method[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37(3): 2654-2662.
[25] 杜晓刚, 路文杰, 雷涛, 等. 亮度信噪比引导Transformer的低照度图像增强[J]. 计算机工程与应用, 2025, 61(6): 263-272.
DU X G, LU W J, LEI T, et al. Low-light image enhancement using brightness and signal-to-noise ratio guided transformer[J]. Computer Engineering and Applications, 2025, 61(6): 263-272.
[26] BYCHKOVSKY V, PARIS CHAN E, et al. Learning photographic global tonal adjustment with a database of input/output image pairs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2011: 97-104.
[27] LEE C, KIM C S. Contrast enhancement based on layered difference representation[C]//Proceedings of the 2012 19th IEEE International Conference on Image Processing. Piscataway: IEEE, 2012: 965-968.
[28] YAO S S, LIN W S, ONG E, et al. Contrast signal-to-noise ratio for image quality assessment[C]//Proceedings of the IEEE International Conference on Image Processing. Piscataway: IEEE, 2005: 397-400.
[29] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[30] MITTAL A, SOUNDARARAJAN R, BOVIK A C. Making a “completely blind” image quality analyzer[J]. IEEE Signal Processing Letters, 2013, 20(3): 209-212.
[31] MA C, YANG C Y, YANG X K, et al. Learning a no-reference quality metric for single-image super-resolution[J]. Computer Vision and Image Understanding, 2017, 158: 1-16.