DLCINet: dual-branch lightness–chromaticity interaction network for low

Abstract Low-light image enhancement aims to restore visible details and faithful colors from images acquired under insufficient illumination. It is also a latency-sensitive preprocessing component in large-scale video analytics, nighttime surveillance, autonomous systems, and remote-sensing pipelines, where high-resolution frames must be processed continuously on parallel accelerators or distributed computing nodes. Existing methods based on the sRGB color space are prone to color distortion because brightness and color information are strongly coupled. Although luminance-oriented color spaces such as HSV partially decouple these factors, their polar representations introduce color discontinuities and black-plane artifacts. We therefore propose a learnable horizontal/vertical-lightness (HVL) color space and a dual-branch lightness–chromaticity interaction network (DLCINet). HVL combines a Cartesian representation of hue and saturation with a learnable, symmetric lightness-collapse function that attenuates chromatic uncertainty near both dark and bright poles. DLCINet models lightness and chromaticity in separate branches and exchanges complementary information through bidirectional depthwise-separable cross-attention. An Adaptive Enhance Module further regulates residual enhancement through a learnable fusion parameter. The architecture is composed predominantly of convolutional, pointwise, and batched attention operations that map efficiently to GPU parallelism; its measured parameter count, computational cost, and inference throughput are reported in 1.59 Params (M), 6.12 FLOPs (G), and 42 FPS, respectively. Experiments on eight public datasets show competitive quantitative and perceptual performance. Data availability The datasets analyzed during the current study (including LOL, VV, MEF, DICM, NPE, and LIME) are publicly available from their respective original creators. All data sources have been explicitly cited within the article. References Li C, Guo C, Han L, Jiang J, Cheng M-M, Gu J, Loy CC (2022) Low-light image and video enhancement using deep learning: a survey. IEEE Trans Pattern Anal Mach Intell 44(12):9396–9416. https://doi.org/10.1109/TPAMI.2021.3126387 Ibrahim H, Pik Kong NS (2007) Brightness preserving dynamic histogram equalization for image contrast enhancement. IEEE Trans Consum Electron 53(4):1752–1758. https://doi.org/10.1109/TCE.2007.4429280 Abdullah-Al-Wadud M, Kabir MH, Akber Dewan MA, Chae O (2007) A dynamic histogram equalization for image contrast enhancement. IEEE Trans Consum Electron 53(2):593–600. https://doi.org/10.1109/TCE.2007.381734 Land EH (1977) The retinex theory of color vision. Sci Am 237(6):108–129. https://doi.org/10.1038/scientificamerican1277-108 Guo X, Li Y, Ling H (2017) Lime: low-light image enhancement via illumination map estimation. IEEE Trans Image Process 26(2):982–993. https://doi.org/10.1109/TIP.2016.2639450 Liu F, Fan L (2025) A review of advancements in low-light image enhancement using deep learning. Neurocomputing 652:131052. https://doi.org/10.1016/j.neucom.2025.131052 Wei C, Wang W, Yang W, Liu J (2018) Deep Retinex Decomposition for low-light enhancement. https://doi.org/10.48550/arXiv.1808.04560 Zhang Y, Zhang J, Guo X (2019) Kindling the darkness: a practical low-light image enhancer. In: Proceedings of the 27th ACM International Conference on Multimedia. MM ’19. Association for Computing Machinery, New York. pp. 1632–1640. https://doi.org/10.1145/3343031.3350926 Cai Y, Bian H, Lin J, Wang H, Timofte R, Zhang Y (2023) Retinexformer: one-stage retinex-based transformer for low-light image enhancement. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 12470–12479. https://doi.org/10.1109/ICCV51070.2023.01149 Xu X, Wang R, Fu C-W, Jia J (2022) Snr-aware low-light image enhancement. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 17693–17703. https://doi.org/10.1109/CVPR52688.2022.01719 Bai J, Yin Y, He Q, Li Y, Zhang X (2025) Retinexmamba: retinex-based mamba for low-light image enhancement. In: Mahmud M, Doborjeh M, Wong K, Leung ACS, Doborjeh Z, Tanveer M (eds) Neural information processing. Springer, Singapore, pp 427–442 Zhou L, Chen X, Ye B, Jiang X, Zou S, Ji L, Yu Z, Wei J, Zhao Y, Wang T (2025) A low-light image enhancement method based on hsv space. Imag Sci J 73(1):16–29 Chobola T, Liu Y, Zhang H, Schnabel JA, Peng T (2025) Fast context-based low-light image enhancement via neural implicit representations. In: Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G (eds) Computer Vision - ECCV 2024. Springer, Cham, pp 413–430. https://doi.org/10.1007/978-3-031-73016-0_24 Garg A, Pan X-W, Dung L-R (2022) Licent: low-light image enhancement using the light channel of hsl. IEEE Access 10:33547–33560. https://doi.org/10.1109/ACCESS.2022.3161527 Brateanu A, Balmez R, Avram A, Orhei C, Ancuti C (2025) Lyt-net: lightweight yuv transformer-based network for low-light image enhancement. IEEE Signal Process Lett 32:2065–2069. https://doi.org/10.1109/LSP.2025.3563125 Guo X, Hu Q (2023) Low-light image enhancement via breaking down the darkness. Int J Comput Vision 131(1):48–66. https://doi.org/10.1007/s11263-022-01667-9 Gevers T, Gijsenij A, Weijer J, Geusebroek JM (2012) Color in computer vision: fundamentals and applications. The Wiley-IS&T series in imaging science and technologyThe Wiley-IS&T series in imaging science and technologyThe Wiley-IS&T series in imaging science and technology. Wiley, Chichester Yan Q, Feng Y, Zhang C, Pang G, Shi K, Wu P, Dong W, Sun J, Zhang Y (2025) Hvi: a new color space for low-light image enhancement. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5678–5687. https://doi.org/10.1109/CVPR52734.2025.00533 Celik T, Tjahjadi T (2011) Contextual and variational contrast enhancement. IEEE Trans Image Process 20(12):3431–3441. https://doi.org/10.1109/TIP.2011.2157513 Cheng HD, Shi XJ (2004) A simple and effective histogram equalization approach to image enhancement. Digital Signal Processing 14(2):158–170. https://doi.org/10.1016/j.dsp.2003.07.002 Jobson DJ, Rahman Z, Woodell GA (1997) A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans Image Process 6(7):965–976. https://doi.org/10.1109/83.597272 Jobson DJ, Rahman Z, Woodell GA (1997) Properties and performance of a center/surround retinex. IEEE Trans Image Process 6(3):451–462. https://doi.org/10.1109/83.557356 Lore KG, Akintayo A, Sarkar S (2017) Llnet: a deep autoencoder approach to natural low-light image enhancement. Pattern Recogn 61:650–662. https://doi.org/10.1016/j.patcog.2016.06.008 Zhou S, Li C, Change Loy C (2022) Lednet: joint low-light enhancement and deblurring in the dark. In: Avidan S, Brostow G, Cissé M, Farinella GM, Hassner T (eds) Computer vision-ECCV 2022. Springer, Cham, pp 573–589. https://doi.org/10.1007/978-3-031-20068-7_33 Fan G-D, Fan B, Gan M, Chen G-Y, Chen CLP (2022) Multiscale low-light image enhancement network with illumination constraint. IEEE Trans Circuits Syst Video Technol 32(11):7403–7417. https://doi.org/10.1109/TCSVT.2022.3186880 Guo C, Li C, Guo J, Loy CC, Hou J, Kwong S, Cong R (2020) Zero-reference deep curve estimation for low-light image enhancement. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1777–1786. https://doi.org/10.1109/CVPR42600.2020.00185 Li C, Guo C, Loy CC (2022) Learning to enhance low-light image via zero-reference deep curve estimation. IEEE Trans Pattern Anal Mach Intell 44(8):4225–4238. https://doi.org/10.1109/TPAMI.2021.3063604 Ma L, Ma T, Liu R, Fan X, Luo Z (2022) Toward fast, flexible, and robust low-light image enhancement. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5627–5636. https://doi.org/10.1109/CVPR52688.2022.00555 Wu W, Weng J, Zhang P, Wang X, Yang W, Jiang J (2022) Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5891–5900. https://doi.org/10.1109/CVPR52688.2022.00581 Zhang Y, Guo X, Ma J, Liu W, Zhang J (2021) Beyond brightening low-light images. Int J Comput Vision 129(4):1013–1037. https://doi.org/10.1007/s11263-020-01407-x Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN (2017) Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems. Curran Associates Inc, Red Hook. DOIhttps://doi.org/10.48550/arXiv.1706.03762 Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. https://doi.org/10.48550/arXiv.2010.11929 Wang Y, Wan R, Yang W, Li H, Chau L-P, Kot A (2022) Low-light image enhancement with normalizing flow. Proc AAAI Conf Artif Intell 36:2604–2612. https://doi.org/10.1609/aaai.v36i3.20162 Jiang Y, Gong X, Liu D, Cheng Y, Fang C, Shen X, Yang J, Zhou P, Wang Z (2021) Enlightengan: deep light enhancement without paired supervision. IEEE Trans Image Process 30:2340–2349. https://doi.org/10.1109/TIP.2021.3051462 Wang C, Wu H, Jin Z (2023) Fourllie: Boosting low-light image enhancement by fourier frequency information. MM ’23. Association for Computing Machinery, pp. 7459–7469. New York. https://doi.org/10.1145/3581783.3611909 Foley JD, Van Dam A (1982) Fundamentals of interactive computer graphics. Addison-Wesley Longman Publishing Co., Inc., Boston. https://doi.org/10.5555/6684 Atoum Y, Ye M, Ren L, Tai Y, Liu X (2020) Color-wise attention network for low-light image enhancement. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2130–2139. https://doi.org/10.1109/CVPRW50498.2020.00261 Robertson AR (1977) The cie 1976 color-difference formulae. Color Res Appl 2(1):7–11. https://doi.org/10.1002/j.1520-6378.1977.tb00104.x Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612. https://doi.org/10.1109/TIP.2003.819861 Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision-ECCV 2016. Springer, Cham, pp 694–711. https://doi.org/10.1007/978-3-319-46475-6_43 Seif G, Androutsos D (2018) Edge-based loss function for single image super-resolution. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1468–1472.https://doi.org/10.1109/ICASSP.2018.8461664 Yang W, Wang W, Huang H, Wang S, Liu J (2021) Sparse gradient regularized deep retinex network for robust low-light image enhancement. IEEE Trans Image Process 30:2072–2086. https://doi.org/10.1109/TIP.2021.3050850 Vonikakis V, Kouskouridas R, Gasteratos A (2018) On the evaluation of illumination compensation algorithms. Multimed Tools Appl 77(8):9211–9231. https://doi.org/10.1007/s11042-017-4783-x Ma K, Zeng K, Wang Z (2015) Perceptual quality assessment for multi-exposure image fusion. IEEE Trans Image Process 24(11):3345–3356. https://doi.org/10.1109/TIP.2015.2442920 Lee C, Lee C, Kim C-S (2013) Contrast enhancement based on layered difference representation of 2d histograms. IEEE Trans Image Process 22(12):5372–5384. https://doi.org/10.1109/TIP.2013.2284059 Wang S, Zheng J, Hu H-M, Li B (2013) Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Trans Image Process 22(9):3538–3548. https://doi.org/10.1109/TIP.2013.2261309 Wang T, Zhang K, Shen T, Luo W, Stenger B, Lu T (2023) Ultra-high-definition low-light image enhancement: a benchmark and transformer-based method. Proc AAAI Conf Artif Intell 37(3):2654–2662. https://doi.org/10.1609/aaai.v37i3.25364 Zheng N, Zhou M, Dong Y, Rui X, Huang J, Li C, Zhao F (2023) Empowering low-light image enhancer through customized learnable priors. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 12525–12535. https://doi.org/10.1109/ICCV51070.2023.01154 Fu Z, Yang Y, Tu X, Huang Y, Ding X, Ma K-K (2023) Learning a simple low-light image enhancer from paired low-light instances. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22252–22261. https://doi.org/10.1109/CVPR52729.2023.02131 Wang W, Yang H, Fu J, Liu J (2024) Zero-reference low-light enhancement via physical quadruple priors. In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26057–26066. https://doi.org/10.1109/CVPR52733.2024.02462 Hou J, Zhu Z, Hou J, Liu H, Zeng H, Yuan H (2023) Global structure-aware diffusion process for low-light image enhancement. In: Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S (eds) Advances in neural information processing systems, vol 36. Curran Associates Inc., Red Hook, pp 79734–79747 Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. CoRR https://doi.org/10.48550/arXiv.1412.6980arXiv:abs/1412.6980 Loshchilov I, Hutter F (2016) Sgdr: Stochastic gradient descent with warm restarts. https://doi.org/10.48550/arXiv.1412.6980 Liu R, Ma L, Zhang J, Fan X, Luo Z (2021) Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10556–10565. https://doi.org/10.1109/CVPR46437.2021.01042 Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 586–595. https://doi.org/10.1109/CVPR.2018.00068 Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJ, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems, vol 25. Curran Associates Inc, Red Hook Mittal A, Soundararajan R, Bovik AC (2013) Making a “completely blind image quality analyzer. IEEE Signal Process Lett 20(3):209–212. https://doi.org/10.1109/LSP.2012.2227726 Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708. https://doi.org/10.1109/TIP.2012.2214050 Acknowledgements This work was supported by the Sichuan Science and Technology Program, grant number 2026YFHZ0275. Author information Authors and Affiliations Contributions B.S. and T.Y. were involved in conceptualization and writing—original draft; B.S., T.Y., and R.Q. contributed to methodology and investigation; R.Q. and C.L. were involved in implementation; T.Y. and R.Q. contributed to writing—review and editing; C.L. was involved in resources; R.Q. and C.L. contributed to funding acquisition. Corresponding author Ethics declarations Conflict of interest The authors declare no conflict of interest. Ethical approval Not applicable. Additional information Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Rights and permissions Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. About this article Cite this article Su, B., Yi, T., Qu, R. et al. DLCINet: dual-branch lightness–chromaticity interaction network for low-light image enhancement. J Supercomput 82, 724 (2026). https://doi.org/10.1007/s11227-026-08863-1 Received: Accepted: Published: Version of record: DOI: https://doi.org/10.1007/s11227-026-08863-1