HVI-Based Spatial–Frequency-Domain Multi-Scale Fusion for Low-Light Image Enhancement
Source abstract
Abstract
Low-light image enhancement aims to restore images captured under extreme low-light conditions. Existing methods demonstrate that fusing Fourier transform magnitude and phase information within the RGB color space effectively improves enhancement results. Meanwhile, recent advances have demonstrated that certain color spaces based on human visual perception, such as Hue–Value–Intensity (HVI), are superior to RGB for enhancing low-light images. However, these methods neglect the key impact of the coupling relationship between spatial and frequency-domain features on image enhancement. This paper proposes a spatial–frequency-domain multi-scale fusion for low-light image enhancement by exploring the intrinsic relationships among the three channels of HVI space, which consists of a dual-path parallel processing architecture. In the spatial domain, a specifically designed multi-scale feature extraction module systematically captures comprehensive structural information. In the frequency domain, our model establishes deep coupling between spatial features and Fourier transform features in the I-channel. The effectively fused features from both domains synergistically drive an encoder–decoder network to achieve superior image enhancement performance. Extensive experiments on multiple public benchmark datasets show that the proposed method significantly outperforms state-of-the-art approaches in both quantitative metrics and visual quality.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Advanced Image Fusion Techniques · Image Processing Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology/School of Artificial Intelligence, Mine Digitization Engineering Research Center of the Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China
Xuhai College, China University of Mining and Technology, Xuzhou 221008, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Jiangsu Province
References (72)
Show source-provided references
1. Sun, T., Segu, M., Postels, J., Wang, Y., Van Gool, L., Schiele, B., Tombari, F., and Yu, F. (2022, January 18–24). SHIFT: A synthetic driving dataset for continuous multi-task domain adaptation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.02068 ↗
2. A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook10.1109/TIV.2024.3394735 ↗
3. Hong, S., Marinescu, R., Dalca, A.V., Bonkhoff, A.K., Bretzner, M., Rost, N.S., and Golland, P. (2021, January 1). 3D-StyleGAN: A style-based generative adversarial network for generative modeling of three-dimensional medical images. Proceedings of the MICCAI Workshop on Deep Generative Models, Strasbourg, France.10.1007/978-3-030-88210-5_3 ↗
4. Cap, Q.H., Fukuda, A., and Iyatomi, H. (2025). A practical framework for unsupervised structure preservation medical image enhancement. Biomed. Signal Process. Control, 100.10.1016/j.bspc.2024.106918 ↗
5. Rabbi, J., Ray, N., Schubert, M., Chowdhury, S., and Chao, D. (2020). Small-object detection in remote sensing images with end-to-end edge-enhanced GAN and object detector network. Remote Sens., 12.10.20944/preprints202003.0313.v2 ↗
6. Exploring Distortion Prior With Latent Diffusion Models for Remote Sensing Image Compression
7. Kim, H.U., Koh, Y.J., and Kim, C.S. (2020, January 23–28). Global and local enhancement networks for paired and unpaired image enhancement. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58595-2_21 ↗
8. Jung, H., Jang, H., Ha, N., and Sohn, K. (2021, January 2–9). Deep low-contrast image enhancement using structure tensor representation. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.10.1609/aaai.v35i2.16266 ↗
9. Liu, R., Ma, L., Zhang, J., Fan, X., and Luo, Z. (2021, January 20–25). Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01042 ↗
10. Jiang, K., Wang, Z., Wang, Z., Chen, C., Yi, P., Lu, T., and Lin, C.W. (March, January 22). Degrade is upgrade: Learning degradation for low-light image enhancement. Proceedings of the AAAI Conference on Artificial Intelligence, Online.
11. Jin, Y., Yang, W., and Tan, R.T. (2022, January 23–27). Unsupervised night image enhancement: When layer decomposition meets light-effects suppression. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-19836-6_23 ↗
12. Wang, C., Wu, H., and Jin, Z. (2023, January 29). Fourllie: Boosting low-light image enhancement by fourier frequency information. Proceedings of the 31st ACM International Conference on Multimedia, Ottawa, ON, Canada.10.1145/3581783.3611909 ↗
13. Zhang, T., Liu, P., Zhao, M., and Lv, H. (November, January 28). DMFourLLIE: Dual-stage and multi-branch fourier network for low-light image enhancement. Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, VIC, Australia.
14. Jiang, H., Luo, A., Liu, X., Han, S., and Liu, S. (October, January 29). Lightendiffusion: Unsupervised low-light image enhancement with latent-retinex diffusion models. Proceedings of the European Conference on Computer Vision, Milan, Italy.
15. Yan, Q., Feng, Y., Zhang, C., Pang, G., Shi, K., Wu, P., Dong, W., Sun, J., and Zhang, Y. (2025, January 11–15). Hvi: A new color space for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR52734.2025.00533 ↗
16. Low illumination video image enhancement10.1109/JPHOT.2020.3010966 ↗
17. Better than reference in low-light image enhancement: Conditional re-enhancement network10.1109/TIP.2021.3135473 ↗
18. Low-light image enhancement via breaking down the darkness10.1007/s11263-022-01667-9 ↗
19. Adaptive histogram equalization and its variations10.1016/S0734-189X(87)80186-X ↗
20. Contrast limited adaptive histogram equalization image processing to improve the detection of simulated spiculations in dense mammograms10.1007/BF03178082 ↗
21. A histogram modification framework and its application for image contrast enhancement10.1109/TIP.2009.2021548 ↗
22. Contrast enhancement based on layered difference representation of 2D histograms10.1109/TIP.2013.2284059 ↗
23. An effective histogram modification scheme for image contrast enhancement10.1016/j.image.2017.07.009 ↗
24. A multiscale retinex for bridging the gap between color images and the human observation of scenes10.1109/83.597272 ↗
25. Retinex processing for automatic image enhancement10.1117/1.1636183 ↗
26. Fu, X., Zeng, D., Huang, Y., Zhang, X.P., and Ding, X. (2016, January 27–30). A weighted variational model for simultaneous reflectance and illumination estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.304 ↗
27. Structure-revealing low-light image enhancement via robust retinex model10.1109/TIP.2018.2810539 ↗
28. Star: A structure and texture aware retinex model10.1109/TIP.2020.2974060 ↗
29. Multi-purpose oriented single nighttime image haze removal based on unified variational retinex model10.1109/TCSVT.2022.3214430 ↗
30. Lv, F., Liu, B., and Lu, F. (2020, January 12–16). Fast enhancement for non-uniform illumination images using light-weight CNNs. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.10.1145/3394171.3413925 ↗
31. Zhang, F., Li, Y., You, S., and Fu, Y. (2021, January 20–25). Learning temporal consistency for low light video enhancement from single images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00493 ↗
32. Ma, L., Ma, T., Liu, R., Fan, X., and Luo, Z. (2022, January 18–24). Toward fast, flexible, and robust low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00555 ↗
33. LE-GAN: Unsupervised low-light image enhancement network using attention module and identity invariant loss10.1016/j.knosys.2021.108010 ↗
34. Fu, Z., Yang, Y., Tu, X., Huang, Y., Ding, X., and Ma, K.K. (2023, January 17–24). Learning a simple low-light image enhancer from paired low-light instances. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.02131 ↗
35. Wu, Y., Pan, C., Wang, G., Yang, Y., Wei, J., Li, C., and Shen, H.T. (2023, January 17–24). Learning semantic-aware knowledge guidance for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00166 ↗
36. Global structure-aware diffusion process for low-light image enhancement
37. R2rnet: Low-light image enhancement via real-low to real-normal network10.1016/j.jvcir.2022.103712 ↗
38. Guo, C., Li, C., Guo, J., Loy, C.C., Hou, J., Kwong, S., and Cong, R. (2020, January 13–19). Zero-reference deep curve estimation for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00185 ↗
39. Zheng, C., Shi, D., and Shi, W. (2021, January 10–17). Adaptive unfolding total variation network for low-light image enhancement. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00440 ↗
40. Yi, X., Xu, H., Zhang, H., Tang, L., and Ma, J. (2023, January 1–6). Diff-retinex: Rethinking low-light image enhancement with a generative diffusion model. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France.10.1109/ICCV51070.2023.01130 ↗
41. Cai, Y., Bian, H., Lin, J., Wang, H., Timofte, R., and Zhang, Y. (2023, January 4–6). Retinexformer: One-stage retinex-based transformer for low-light image enhancement. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France.10.1109/ICCV51070.2023.01149 ↗
42. Feng, Y., Hou, S., Lin, H., Zhu, Y., Wu, P., Dong, W., Sun, J., Yan, Q., and Zhang, Y. (2024, January 17–18). Difflight: Integrating content and detail for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW63382.2024.00619 ↗
43. Xu, Q., Zhang, R., Zhang, Y., Wang, Y., and Tian, Q. (2021, January 20–25). A fourier-based framework for domain generalization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01415 ↗
44. Fuoli, D., Van Gool, L., and Timofte, R. (2021, January 10–17). Fourier space losses for efficient perceptual image super-resolution. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00236 ↗
45. Jiang, L., Dai, B., Wu, W., and Loy, C.C. (2021, January 10–17). Focal frequency loss for image reconstruction and synthesis. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.01366 ↗
46. Guo, X., Fu, X., Zhou, M., Huang, Z., Peng, J., and Zha, Z.J. (2022, January 23–29). Exploring Fourier Prior for Single Image Rain Removal. Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22), Vienna, Austria.10.24963/ijcai.2022/131 ↗
47. Huang, J., Liu, Y., Zhao, F., Yan, K., Zhang, J., Huang, Y., Zhou, M., and Xiong, Z. (2022, January 23–27). Deep fourier-based exposure correction network with spatial-frequency interaction. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-19800-7_10 ↗
48. Li, C., Guo, C.L., Zhou, M., Liang, Z., Zhou, S., Feng, R., and Loy, C.C. (2023). Embedding fourier for ultra-high-definition low-light image enhancement. arXiv.
49. Lv, X., Zhang, S., Wang, C., Zheng, Y., Zhong, B., Li, C., and Nie, L. (2024, January 16–22). Fourier priors-guided diffusion for zero-shot joint low-light enhancement and deblurring. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.02398 ↗
50. Wei, C., Wang, W., Yang, W., and Liu, J. (2018). Deep retinex decomposition for low-light enhancement. arXiv.
51. Sparse gradient regularized deep retinex network for robust low-light image enhancement10.1109/TIP.2021.3050850 ↗
52. Bychkovsky, V., Paris, S., Chan, E., and Durand, F. (2011, January 20–25). Learning photographic global tonal adjustment with a database of input/output image pairs. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, USA.10.1109/CVPR.2011.5995332 ↗
53. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
54. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–23). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
55. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
56. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
57. Loshchilov, I., and Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv.
58. Ying, Z., Li, G., and Gao, W. (2017). A bio-inspired multi-exposure fusion framework for low-light image enhancement. arXiv.
59. Dong, X., Pang, Y., and Wen, J. (2010, January 26–30). Fast efficient algorithm for enhancement of low lighting video. Proceedings of the ACM SIGGRAPH 2010 Posters, Los Angeles, CA, USA.10.1145/1836845.1836920 ↗
60. LIME: Low-light image enhancement via illumination map estimation10.1109/TIP.2016.2639450 ↗
61. A fusion-based enhancing method for weakly illuminated images
62. Naturalness preserved enhancement algorithm for non-uniform illumination images10.1109/TIP.2013.2261309 ↗
63. DSLR: Deep stacked Laplacian restorer for low-light image enhancement10.1109/TMM.2020.3039361 ↗
64. Zhang, Y., Zhang, J., and Guo, X. (2019, January 21–25). Kindling the darkness: A practical low-light image enhancer. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.10.1145/3343031.3350926 ↗
65. Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., and Li, H. (2022, January 18–24). Uformer: A general u-shaped transformer for image restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01716 ↗
66. Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., and Yang, M.H. (2022, January 18–24). Restormer: Efficient transformer for high-resolution image restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00564 ↗
67. Wang, T., Zhang, K., Shen, T., Luo, W., Stenger, B., and Lu, T. (2023, January 7–14). Ultra-high-definition low-light image enhancement: A benchmark and transformer-based method. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v37i3.25364 ↗
68. Beyond brightening low-light images10.1007/s11263-020-01407-x ↗
69. Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H., and Shao, L. (2020, January 23–28). Learning enriched features for real image restoration and enhancement. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58595-2_30 ↗
70. Xu, X., Wang, R., Fu, C.W., and Jia, J. (2022, January 18–24). Snr-aware low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01719 ↗
71. Learning to enhance low-light image via zero-reference deep curve estimation
72. Enlightengan: Deep light enhancement without paired supervision10.1109/TIP.2021.3051462 ↗