A High-Speed and Structure-Preserving Retinex Method Based on a Complex Exponential Kernel: XCR
DOI:
https://doi.org/10.51094/jxiv.1961Keywords:
Low-light image enhancement, Retinex theory, XCR, structure preservation, separable kernel, high-speed processing, image enhancementAbstract
This paper presents eXponential-Cos Retinex (XCR), a new Retinex-based enhancement method designed to achieve both structure preservation and high-speed processing for low-light images. Conventional approaches such as Single-Scale Retinex (SSR), Multi-Scale Retinex (MSR), and illumination-map estimation methods including LIME often suffer from noise amplification, halo artifacts, color distortions, and high computational cost.
The proposed XCR introduces a novel separable kernel analytically derived from complex exponential and cosine functions, enabling stable illumination estimation while effectively preserving structural information. In addition, adaptive reflectance amplification based on illumination values combined with γ-correction suppresses excessive changes in bright regions and produces more natural visual results.
Experimental evaluations demonstrate that XCR achieves higher Structural Similarity Index (SSIM) and significantly faster processing times than existing Retinex-based methods, exhibiting strong real-time performance. These results indicate that XCR is a promising new alternative within the Retinex family for low-light image enhancement.
Conflicts of Interest Disclosure
The authors declare no conflict of interest.Downloads *Displays the aggregated results up to the previous day.
References
E. H. Land and J. J. McCann, “Lightness and Retinex Theory,” JOSA, 1971.
D. J. Jobson, Z. Rahman, and G. A. Woodell, “A Multiscale Retinex for Bridging the Gap ...,” TIP, 1997.
Z. Rahman, D. J. Jobson, and G. A. Woodell, “Multiscale Retinex for Color Image Enhancement,” ICIP, 1996.
D. J. Jobson, Z. Rahman, and G. A. Woodell, “Properties and Performance of a Center/Surround Retinex,” TIP, 1997.
X. Guo, Y. Li, and H. Ling, “LIME: Low-Light Image Enhancement via Illumination Map Estimation,” TIP, 2017.
S. Wang et al., “Naturalness Preserved Enhancement Algorithm... (NPE),” TIP, 2013.
R. Kimmel et al., “A Variational Framework for Retinex,” IJCV, 2003.
H. Li, X. Wu, and M. S. Drew, Fundamentals of Retinex Theory, Springer, 2014.
Y. Ren et al., “Enhancing Low Light Images using Near-infrared Flash Images,” TIP, 2016.
X. Fu et al., “A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation,” CVPR, 2016.
Downloads
Posted
Submitted: 2025-11-16 12:52:41 UTC
Published: 2025-11-20 09:58:24 UTC
License
Copyright (c) 2025
Toma Okugawa
This work is licensed under a Creative Commons Attribution 4.0 International License.
