LL-Refiner: Learning Adaptive Refinement for Ultra-High-Definition Low-Light Image Enhancement

Xunpeng Yi; Qinglong Yan; Yibing Zhang; Zongrong Li; Hao Zhang; Zhanchuan Cai; Jiayi Ma

doi:10.1109/JAS.2026.125939

Volume 13 Issue 6

Jun. 2026

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 18.3, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2026 > 13(6): 1288-1300

X. Yi, Q. Yan, Y. Zhang, Z. Li, H. Zhang, Z. Cai, and J. Ma, “LL-Refiner: Learning adaptive refinement for ultra-high-definition low-light image enhancement,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 6, pp. 1288–1300, Jun. 2026. doi: 10.1109/JAS.2026.125939

Citation:

X. Yi, Q. Yan, Y. Zhang, Z. Li, H. Zhang, Z. Cai, and J. Ma, “LL-Refiner: Learning adaptive refinement for ultra-high-definition low-light image enhancement,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 6, pp. 1288–1300, Jun. 2026. doi: 10.1109/JAS.2026.125939

Citation:

PDF( 40039 KB)

LL-Refiner: Learning Adaptive Refinement for Ultra-High-Definition Low-Light Image Enhancement

doi: 10.1109/JAS.2026.125939

Funds: This work was supported by the National Natural Science Foundation of China (625B2135, 62506268, and 62276192)

More Information

Author Bio:
Xunpeng Yi received the B.E. degree in the Electronic Information School, Wuhan University in 2023. He is currently working toward the Ph.D. degree in the Electronic Information School, Wuhan University. He has first-authored several refereed journal and conference papers, including IEEE Transactions on Pattern Analysis and Machine Intelligence, Conference on Computer Vision and Pattern Recognition (CVPR), International Conference on Computer Vision (ICCV), etc. His research interests include computer vision and image processing

Qinglong Yan received the B.E. degree from the School of Mechanical Engineering and Electronic Information, China University of Geosciences in 2023, and the M.S. degree from the Electronic Information School, Wuhan University in 2025. He is currently pursuing the Ph.D. degree with the Electronic Information School, Wuhan University. His research interests include computer vision, machine learning, and pattern recognition

Yibing Zhang received the B.E. degree from Electronics Information School, Wuhan University in 2025. He is currently a Ph.D. student with the Electronic Information School, Wuhan University. His research interests include computer vision, machine learning, and pattern recognition

Zongrong Li received the B.S. and M.S. degrees from the School of Mathematical Sciences, Beihang University in 2019 and 2022, respectively. He is currently working as an electronic metering engineer at the China Electric Power Research Institute. His research interests include deep learning and quantum metrology

Hao Zhang received the B.E. degree from the School of Mechanical Engineering and Electronic Information, China University of Geosciences in 2019, the M.S. and Ph.D. degrees from the Electronic Information School, Wuhan University in 2021 and 2024, respectively. He is currently a Postdoctoral Researcher with the Electronic Information School, Wuhan University. He has first-authored over 10 refereed journal and conference papers, including IEEE Transactions on Pattern Analysis and Machine Intelligence, International Journal of Computer Vision, Conference on Computer Vision and Pattern Recognition (CVPR), NeurIPS, AAAI, etc. He is an Area Editor of Information Fusion. His research interests include computer vision, machine learning, and pattern recognition

Zhanchuan Cai received the Ph.D. degree in computer software and theory from Sun Yat-sen University in 2007. He is currently a Professor at the School of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China, where he is also with the State Key Laboratory of Lunar and Planetary Sciences. He has authored more than 100 articles in journals and refereed conferences. His research interests include remote sensing data processing and analysis, intelligent information processing, image processing and computer graphics, and multimedia information security

Jiayi Ma received the B.S. degree in information and computing science and the Ph.D. degree in control science and engineering from the Huazhong University of Science and Technology in 2008 and 2014, respectively. He is currently a Professor with the Electronic Information School, and also with the School of Robotics, Wuhan University. He has coauthored more than 400 refereed journal and conference papers, including Cell, IEEE Transactions on Pattern Analysis and Machine Intelligence, International Journal of Computer Vision, etc. He is a recipient of the IEEE SPS Best Paper Award 2025, the Information Fusion Best Paper Award 2024, and the Hsue-shen Tsien Paper Award 2023. He is a Co Editor-in-Chief of Information Fusion, an Associate Editor of IEEE Transactions on Image Processing and IEEE/CAA Journal of Automatica Sinica, and a Youth Editor of The Innovation and Fundamental Research
Corresponding author: Hao Zhang, e-mail: zhanghao@whu.edu.cn; Jiayi Ma, e-mail: jiayima@whu.edu.cn
Received Date: 2025-10-20
Revised Date: 2026-01-08
Accepted Date: 2026-01-24

Abstract

Abstract

Low-light image enhancement aims to address various degradations in low-light conditions, such as low illumination, noise pollution, color distortion, and missing scene content. With advances in digital imaging technology, the resolution of captured images has seen substantial improvements. This poses new challenges in achieving good enhancement performance for multi-scale details in ultra-high-definition images, as well as in managing the overhead for supporting the use of consumer-grade GPUs. In this paper, we proposed learning the adaptive refinement framework for ultra-high-definition image enhancement, termed LL-Refiner. It integrates the advantages of hierarchical adaptive refinement guided by coarse enhancement results to enhance the ultra-high-definition images. In detail, firstly, we conduct the coarse enhancement on the low resolution image by employing a Transformer-based coarse enhancement network. Secondly, the coarse enhancement output is fed into the adapted refinement injection. It assigns resolution-aware inputs as guidance to the corresponding adaptive aggregation module, which interacts with the backbone features of the adaptive refinement network. Ultimately, the adaptive refinement network incorporates a combination of hierarchical dense residual connection modules and lightweight convolutional modules at different resolution stages. Also, it integrates a multi-scale enhanced perceptual loss to progressively achieve ultra-high-definition image enhancement. Extensive experiments on ultra-high-definition image enhancement validate the effectiveness and superiority of the proposed method. Our code is publicly available at https://github.com/XunpengYi/LL-Refiner.
- Adaptive refinement,
- low-light image enhancement,
- ultra-high-definition image

FullText(HTML)

References(60)

References

[1]	J. Liu, D. Xu, W. Yang, M. Fan, and H. Huang, “Benchmarking low-light image enhancement and beyond,” Int. J. Comput. Vis., vol. 129, no. 4, pp. 1153–1184, Jan. 2021. doi: 10.1007/s11263-020-01418-8
[2]	D. Liang, Z. Xu, L. Li, M. Wei, and S. Chen, “PIE: Physics-inspired low-light enhancement,” Int. J. Comput. Vis., vol. 132, no. 9, pp. 3911–3932, Apr. 2024. doi: 10.1007/s11263-024-01995-y
[3]	D. Liang, L. Li, M. Wei, S. Yang, L. Zhang, W. Yang, Y. Du, and H. Zhou, “Semantically contrastive learning for low-light image enhancement,” in Proc. 36th AAAI Conf. Artificial Intelligence, 2022, pp. 1555−1563.
[4]	J. A. Stark, “Adaptive image contrast enhancement using generalizations of histogram equalization,” IEEE Trans. Image Process., vol. 9, no. 5, pp. 889–896, May 2000. doi: 10.1109/83.841534
[5]	H.-D. Cheng and X. Shi, “A simple and effective histogram equalization approach to image enhancement,” Digit. Signal Process., vol. 14, no. 2, pp. 158–170, Mar. 2004. doi: 10.1016/j.dsp.2003.07.002
[6]	C. Lee, C. Lee, and C.-S. Kim, “Contrast enhancement based on layered difference representation of 2D histograms,” IEEE Trans. Image Process., vol. 22, no. 12, pp. 5372–5384, Dec. 2013. doi: 10.1109/TIP.2013.2284059
[7]	X. Guo, Y. Li, and H. Ling, “LIME: Low-light image enhancement via illumination map estimation,” IEEE Trans. Image Process., vol. 26, no. 2, pp. 982–993, Feb. 2017. doi: 10.1109/TIP.2016.2639450
[8]	X. Ren, M. Li, W.-H. Cheng, and J. Liu, “Joint enhancement and denoising method via sequential decomposition,” in Proc. IEEE Int. Symp. Circuits and Systems, Florence, Italy, 2018, pp. 1−5.
[9]	C. Li, J. Guo, F. Porikli, and Y. Pang, “LightenNet: A Convolutional Neural Network for weakly illuminated image enhancement,” Pattern Recogn. Lett., vol. 104, pp. 15–22, Mar. 2018. doi: 10.1016/j.patrec.2018.01.010
[10]	C. Li, C. Guo, and C. C. Loy, “Learning to enhance low-light image via zero-reference deep curve estimation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 8, pp. 4225–4238, Aug. 2022.
[11]	Y. Zhang, X. Guo, J. Ma, W. Liu, and J. Zhang, “Beyond brightening low-light images,” Int. J. Comput. Vis., vol. 129, no. 4, pp. 1013–1037, Jan. 2021. doi: 10.1007/s11263-020-01407-x
[12]	R. Liu, L. Ma, J. Zhang, X. Fan, and Z. Luo, “Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Nashville, USA, 2021, pp. 10556−10565.
[13]	W. Wu, J. Weng, P. Zhang, X. Wang, W. Yang, and J. Jiang, “URetinex-Net: Retinex-based deep unfolding network for low-light image enhancement,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 5891−5900.
[14]	J. Pan, D. Zhai, Y. Bai, J. Jiang, D. Zhao, and X. Liu, “ChebyLighter: Optimal curve estimation for low-light image enhancement,” in Proc. 30th ACM Int. Conf. Multimedia, Lisboa, Portugal, 2022, pp. 1358−1366.
[15]	W. Wu, J. Weng, P. Zhang, X. Wang, W. Yang, and J. Jiang, “Interpretable optimization-inspired unfolding network for low-light image enhancement,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 4, pp. 2545–2562, Apr. 2025. doi: 10.1109/TPAMI.2024.3524538
[16]	Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, “Swin transformer: Hierarchical vision transformer using shifted windows,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Montreal, Canada, 2021, pp. 9992−10002.
[17]	Z. Wang, X. Cun, J. Bao, W. Zhou, J. Liu, and H. Li, “Uformer: A general U-shaped transformer for image restoration,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 17662−17672.
[18]	S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, and M.-H. Yang, “Restormer: Efficient transformer for high-resolution image restoration,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 5718−5729.
[19]	T. Wang, K. Zhang, T. Shen, W. Luo, B. Stenger, and T. Lu, “Ultra-high-definition low-light image enhancement: A benchmark and transformer-based method,” in Proc. 37th AAAI Conf. Artificial Intelligence, Washington, USA, 2023, pp. 2654−2662.
[20]	Z. Jin, Y. Qiu, K. Zhang, H. Li, and W. Luo, “MB-TaylorFormer V2: Improved multi-branch linear transformer expanded by Taylor formula for image restoration,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 7, pp. 5990–6005, Jul. 2025. doi: 10.1109/TPAMI.2025.3559891
[21]	K. Zhang, D. Li, W. Luo, W. Ren, and W. Liu, “Enhanced spatio-temporal interaction learning for video deraining: Faster and better,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 1, pp. 1287–1293, Jan. 2023. doi: 10.1109/TPAMI.2022.3148707
[22]	K. Zhang, R. Li, Y. Yu, W. Luo, and C. Li, “Deep dense multi-scale network for snow removal using semantic and depth priors,” IEEE Trans. Image Process., vol. 30, pp. 7419–7431, Aug. 2021. doi: 10.1109/TIP.2021.3104166
[23]	K. Zhang, W. Luo, Y. Zhong, L. Ma, W. Liu, and H. Li, “Adversarial spatio-temporal learning for video deblurring,” IEEE Trans. Image Process., vol. 28, no. 1, pp. 291–301, Jan. 2019. doi: 10.1109/TIP.2018.2867733
[24]	J. Hou, Z. Zhu, J. Hou, H. Liu, H. Zeng, and H. Yuan, “Global structure-aware diffusion process for low-light image enhancement,” in Proc. 37th Int. Conf. Neural Information Processing Systems, New Orleans, USA, 2023, Art. no. 3490.
[25]	H. Jiang, A. Luo, X. Liu, S. Han, and S. Liu, “LightenDiffusion: Unsupervised low-light image enhancement with latent-Retinex diffusion models,” in Proc. 18th European Conf. Computer Vision, Milan, Italy, 2024, pp. 161−179.
[26]	W. Wang, H. Yang, J. Fu, and J. Liu, “Zero-reference low-light enhancement via physical quadruple priors,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2024, pp. 26057−26066.
[27]	X. Yi, H. Xu, H. Zhang, L. Tang, and J. Ma, “Diff-Retinex++: Retinex-driven reinforced diffusion model for low-light image enhancement,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 8, pp. 6823–6841, Aug. 2025. doi: 10.1109/TPAMI.2025.3563612
[28]	Y. Cai, H. Bian, J. Lin, H. Wang, R. Timofte, and Y. Zhang, “Retinexformer: One-stage Retinex-based transformer for low-light image enhancement,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 12470−12479.
[29]	C. Wang, J. Pan, W. Wang, G. Fu, S. Liang, M. Wang, X.-M. Wu, and J. Liu, “Correlation matching transformation transformers for UHD image restoration,” in Proc. 38th AAAI Conf. Artificial Intelligence, Vancouver, Canada, 2024, pp. 5336−5344.
[30]	S. M. Pizer, E. P. Amburn, J. D. Austin, R. Cromartie, A. Geselowitz, T. Greer, B. Ter Haar Romeny, J. B. Zimmerman, and K. Zuiderveld, “Adaptive histogram equalization and its variations,” Comput. Vis., Graphics, Image Process., vol. 39, no. 3, pp. 355–368, Sep. 1987. doi: 10.1016/S0734-189X(87)80186-X
[31]	D. J. Jobson, Z. Rahman, and G. A. Woodell, “Properties and performance of a center/surround retinex,” IEEE Trans. Image Process., vol. 6, no. 3, pp. 451–462, Mar. 1997. doi: 10.1109/83.557356
[32]	C. Chen, Q. Chen, M. Do, and V. Koltun, “Seeing motion in the dark,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Seoul, Korea (South), 2019, pp. 3184−3193.
[33]	Z. Fu, Y. Yang, X. Tu, Y. Huang, X. Ding, and K.-K. Ma, “Learning a simple low-light image enhancer from paired low-light instances,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Vancouver, Canada, 2023, pp. 22252−22261.
[34]	K. Jiang, R. Wang, Y. Xiao, J. Jiang, X. Xu, and T. Lu, “Image enhancement via associated perturbation removal and texture reconstruction learning,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 11, pp. 2253–2269, Nov. 2024. doi: 10.1109/JAS.2024.124521
[35]	H. Liu, Q. Zhang, Y. Hu, H. Zeng, and B. Fan, “Unsupervised multi-expert learning model for underwater image enhancement,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 708–722, Mar. 2024. doi: 10.1109/JAS.2023.123771
[36]	C. Wei, W. Wang, W. Yang, and J. Liu, “Deep Retinex decomposition for low-light enhancement,” in Proc. British Machine Vision Conf. 2018, Newcastle, UK, 2018. Art. no. 155.
[37]	C. Guo, C. Li, J. Guo, C. C. Loy, J. Hou, S. Kwong, and R. Cong, “Zero-reference deep curve estimation for low-light image enhancement,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2020, pp. 1777−1786.
[38]	L. Ma, T. Ma, R. Liu, X. Fan, and Z. Luo, “Toward fast, flexible, and robust low-light image enhancement,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 5627−5636.
[39]	Y. Jiang, X. Gong, D. Liu, Y. Cheng, C. Fang, X. Shen, J. Yang, P. Zhou, and Z. Wang, “EnlightenGAN: Deep light enhancement without paired supervision,” IEEE Trans. Image Process., vol. 30, pp. 2340–2349, Jan. 2021. doi: 10.1109/TIP.2021.3051462
[40]	N. Zheng, M. Zhou, Y. Dong, X. Rui, J. Huang, C. Li, and F. Zhao, “Empowering low-light image enhancer through customized learnable priors,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 12525−12535.
[41]	S. Yang, M. Ding, Y. Wu, Z. Li, and J. Zhang, “Implicit neural representation for cooperative low-light image enhancement,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 12872−12881.
[42]	H. Xu, H. Zhang, X. Yi, and J. Ma, “CRetinex: A progressive color-shift aware Retinex model for low-light image enhancement,” Int. J. Comput. Vis., vol. 132, no. 9, pp. 3610–3632, Apr. 2024. doi: 10.1007/s11263-024-02065-z
[43]	Y. Yin, D. Xu, C. Tan, P. Liu, Y. Zhao, and Y. Wei, “CLE diffusion: Controllable light enhancement diffusion model,” in Proc. 31st ACM Int. Conf. Multimedia, Ottawa, Canada, 2023, pp. 8145−8156.
[44]	T. Wang, K. Zhang, Y. Zhang, W. Luo, B. Stenger, T. Lu, T.-K. Kim, and W. Liu, “LLDiffusion: Learning degradation representations in diffusion models for low-light image enhancement,” Pattern Recogn., vol. 166, Art. no. 111628, Oct. 2025.
[45]	X. Yi, H. Xu, H. Zhang, L. Tang, and J. Ma, “Diff-Retinex: Rethinking low-light image enhancement with a generative diffusion model,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 12268−12277.
[46]	Y. Liu, T. Huang, W. Dong, F. Wu, X. Li, and G. Shi, “Low-light image enhancement with multi-stage residue quantization and brightness-aware attention,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 12106−12115.
[47]	C. Li, C.-L. Guo, M. Zhou, Z. Liang, S. Zhou, R. Feng, and C. C. Loy, “Embedding Fourier for ultra-high-definition low-light image enhancement,” in Proc. 11th Int. Conf. Learning Representations, Kigali, Rwanda, 2023.
[48]	K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proc. 3rd Int. Conf. Learning Representations, San Diego, USA, 2015.
[49]	A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, et al., “PyTorch: An imperative style, high-performance deep learning library,” in Proc. 33rd Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2019, Art. no. 721.
[50]	I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in Proc. 7th Int. Conf. Learning Representations, New Orleans, USA, 2019.
[51]	Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Trans. Image Process., vol. 13, no. 4, pp. 600–612, Apr. 2004. doi: 10.1109/TIP.2003.819861
[52]	R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The unreasonable effectiveness of deep features as a perceptual metric,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 586−595.
[53]	M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “GANs trained by a two time-scale update rule converge to a local Nash equilibrium,” in Proc. 31st Int. Conf. Neural Information Processing Systems, Long Beach, USA, 2017, pp. 6629−6640.
[54]	Y. Li, K. Xu, G. P. Hancke, and R. W. H. Lau, “Color shift estimation-and-correction for image enhancement,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2024, pp. 25389−25398.
[55]	C. Hu, T. Chen, D. Jing, K. Hu, Y. Guo, X. Jing, and P. Liu, “ⅡAG-CoFlow: Inter- and intra-channel attention transformer and complete flow for low-light image enhancement with application to night traffic monitoring images,” IEEE Trans. Intell. Transport. Syst., vol. 26, no. 5, pp. 6904–6922, May 2025. doi: 10.1109/tits.2025.3526845
[56]	D. Zheng, X.-M. Wu, S. Yang, J. Zhang, J.-F. Hu, and W.-S. Zheng, “Selective hourglass mapping for universal image restoration based on diffusion model,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2024, pp. 25445−25455.
[57]	C. Zhao, Z. Chen, Y. Xu, E. Gu, J. Li, Z. Yi, Q. Wang, J. Yang, and Y. Tai, “From zero to detail: Deconstructing ultra-high-definition image restoration from progressive spectral perspective,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Nashville, USA, 2025, Art. no. 17935.
[58]	L. Yang, B. Kang, Z. Huang, X. Xu, J. Feng, and H. Zhao, “Depth anything: Unleashing the power of large-scale unlabeled data,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2024, pp. 10371−10381.
[59]	A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, et al., “An image is worth 16×16 words: Transformers for image recognition at scale,” in Proc. 9th Int. Conf. Learning Representations, 2021.
[60]	J. Ke, Q. Wang, Y. Wang, P. Milanfar, and F. Yang, “MUSIQ: Multi-scale image quality transformer,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Montreal, Canada, 2021, pp. 5128−5137.