Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization (2403.01142v1)

Published 2 Mar 2024 in cs.CV, cs.NA, and math.NA

Abstract: Prior-based methods for low-light image enhancement often face challenges in extracting available prior information from dim images. To overcome this limitation, we introduce a simple yet effective Retinex model with the proposed edge extraction prior. More specifically, we design an edge extraction network to capture the fine edge features from the low-light image directly. Building upon the Retinex theory, we decompose the low-light image into its illumination and reflectance components and introduce an edge-guided Retinex model for enhancing low-light images. To solve the proposed model, we propose a novel inertial Bregman alternating linearized minimization algorithm. This algorithm addresses the optimization problem associated with the edge-guided Retinex model, enabling effective enhancement of low-light images. Through rigorous theoretical analysis, we establish the convergence properties of the algorithm. Besides, we prove that the proposed algorithm converges to a stationary point of the problem through nonconvex optimization theory. Furthermore, extensive experiments are conducted on multiple real-world low-light image datasets to demonstrate the efficiency and superiority of the proposed scheme.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. E. H. Land, “The Rretinex theory of color vision,” Scientific American, vol. 237, no. 6, pp. 108–129, 1977.
  2. L. Ma, R. Liu, J. Zhang, X. Fan, and Z. Luo, “Learning deep context-sensitive decomposition for low-light image enhancement,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 10, pp. 5666–5680, 2021.
  3. J. Li, J. Li, F. Fang, F. Li, and G. Zhang, “Luminance-aware pyramid network for low-light image enhancement,” IEEE Transactions on Multimedia, vol. 23, pp. 3153–3165, 2020.
  4. R. Liu, L. Ma, Y. Zhang, X. Fan, and Z. Luo, “Underexposed image correction via hybrid priors navigated deep propagation,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 8, pp. 3425–3436, 2021.
  5. W. Wang, N. Sun, and M. K. Ng, “A variational gamma correction model for image contrast enhancement,” Inverse Problems and Imaging, vol. 13, no. 3, pp. 461–478, 2019.
  6. W. Wang, C. Zhang, and M. K. Ng, “Variational model for simultaneously image denoising and contrast enhancement,” Optics Express, vol. 28, no. 13, pp. 18 751–18 777, 2020.
  7. F. Jia, H. S. Wong, T. Wang, and T. Zeng, “A reflectance re-weighted Retinex model for non-uniform and low-light image enhancement,” Pattern Recognition, vol. 144, p. 109823, 2023.
  8. Z. Gu, F. Li, F. Fang, and G. Zhang, “A novel Rretinex-based fractional-order variational model for images with severely low light,” IEEE Transactions on Image Processing, vol. 29, pp. 3239–3253, 2019.
  9. Q. Ma, Y. Wang, and T. Zeng, “Retinex-based variational framework for low-light image enhancement and denoising,” IEEE Transactions on Multimedia, 2022.
  10. M. K. Ng and W. Wang, “A total variation model for Retinex,” SIAM Journal on Imaging Sciences, vol. 4, no. 1, pp. 345–365, 2011.
  11. H. Chang, M. K. Ng, W. Wang, and T. Zeng, “Retinex image enhancement via a learned dictionary,” Optical Engineering, vol. 54, no. 1, pp. 013 107–013 107, 2015.
  12. X. Ren, W. Yang, W. Cheng, and J. Liu, “LR3M: Robust low-light enhancement via low-rank regularized Retinex model,” IEEE Transactions on Image Processing, vol. 29, pp. 5862–5876, 2020.
  13. F. Jia, T. Wang, and T. Zeng, “Low-light image enhancement via dual reflectance estimation,” Journal of Scientific Computing, vol. 98, no. 2, p. 36, 2024.
  14. F. Jia, S. Mao, X.-C. Tai, and T. Zeng, “A variational model for nonuniform low-light image enhancement,” SIAM Journal on Imaging Sciences, vol. 17, no. 1, pp. 1–30, 2024.
  15. T. Wu, W. Wu, Y. Yang, F.-L. Fan, and T. Zeng, “Retinex image enhancement based on sequential decomposition with a plug-and-play framework,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
  16. C. Wei, W. Wang, W. Yang, and J. Liu, “Deep retinex decomposition for low-light enhancement,” in British Machine Vision Conference, 2018.
  17. X. Liu, Q. Xie, Q. Zhao, H. Wang, and D. Meng, “Low-light image enhancement by Retinex-based algorithm unrolling and adjustment,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
  18. 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 Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 5901–5910.
  19. Q. Ma, Y. Wang, and T. Zeng, “Low-light image enhancement via implicit priors regularized illumination optimization,” IEEE Transactions on Computational Imaging, 2023.
  20. T.-X. Jiang, X.-L. Zhao, H. Zhang, and M. K. Ng, “Dictionary learning with low-rank coding coefficients for tensor completion,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 2, pp. 932–946, 2023.
  21. Y. Chen, X. Gui, J. Zeng, X.-L. Zhao, and W. He, “Combining low-rank and deep plug-and-play priors for snapshot compressive imaging,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–13, 2023.
  22. F. Fang, J. Li, and T. Zeng, “Soft-edge assisted network for single image super-resolution,” IEEE Transactions on Image Processing, vol. 29, pp. 4656–4668, 2020.
  23. F. Fang, J. Li, Y. Yuan, T. Zeng, and G. Zhang, “Multilevel edge features guided network for image denoising,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 9, pp. 3956–3970, 2020.
  24. Y. Fang and T. Zeng, “Learning deep edge prior for image denoising,” Computer Vision and Image Understanding, vol. 200, p. 103044, 2020.
  25. H. Yang, J. Li, L. M. Lui, S. Ying, T. Zeng et al., “Fast MRI reconstruction via edge attention,” Communications in Computational Physics, vol. 33, no. 5, pp. 1409–1431, 2023.
  26. W. Liu, P. Zhang, Y. Lei, X. Huang, J. Yang, and M. Ng, “A generalized framework for edge-preserving and structure-preserving image smoothing,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 10, pp. 6631–6648, 2021.
  27. L. I. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,” Physica D: Nonlinear Phenomena, vol. 60, no. 1-4, pp. 259–268, 1992.
  28. R. Feng, H. Li, L. Wang, Y. Zhong, L. Zhang, and T. Zeng, “Local spatial constraint and total variation for hyperspectral anomaly detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–16, 2021.
  29. X.-G. Lv, J. Liu, F. Li, and X.-L. Yao, “Blind motion deconvolution for binary images,” Journal of Computational and Applied Mathematics, vol. 393, p. 113500, 2021.
  30. T. Wu, X. Gu, Y. Wang, and T. Zeng, “Adaptive total variation based image segmentation with semi-proximal alternating minimization,” Signal Processing, vol. 183, p. 108017, 2021.
  31. T. Wu, Z. Du, Z. Li, F.-L. Fan, and T. Zeng, “VDIP-TGV: Blind image deconvolution via variational deep image prior empowered by total generalized variation,” arXiv preprint arXiv:2310.19477, 2023.
  32. W. Wang and R. Liu, “A saturation-value histogram equalization model for color image enhancement,” Inverse Problems and Imaging, vol. 17, no. 4, pp. 746–766, 2023.
  33. X. Nie, H. Qiao, B. Zhang, and X. Huang, “A nonlocal TV-based variational method for PolSAR data speckle reduction,” IEEE Transactions on Image Processing, vol. 25, no. 6, pp. 2620–2634, 2016.
  34. H. Attouch, J. Bolte, and B. F. Svaiter, “Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward–backward splitting, and regularized Gauss–Seidel methods,” Mathematical Programming, vol. 137, no. 1-2, pp. 91–129, 2013.
  35. J. Bolte, S. Sabach, and M. Teboulle, “Proximal alternating linearized minimization for nonconvex and nonsmooth problems,” Mathematical Programming, vol. 146, no. 1-2, pp. 459–494, 2014.
  36. H. Attouch, J. Bolte, P. Redont, and A. Soubeyran, “Proximal alternating minimization and projection methods for nonconvex problems: An approach based on the Kurdyka-łojasiewicz inequality,” Mathematics of Operations Research, vol. 35, no. 2, pp. 438–457, 2010.
  37. K. Kurdyka, “On gradients of functions definable in o-minimal structures,” in Annales de l’institut Fourier, vol. 48, no. 3, 1998, pp. 769–783.
  38. M. Ahookhosh, A. Themelis, and P. Patrinos, “A Bregman forward-backward linesearch algorithm for nonconvex composite optimization: superlinear convergence to nonisolated local minima,” SIAM Journal on Optimization, vol. 31, no. 1, pp. 653–685, 2021.
  39. J. Bolte, S. Sabach, M. Teboulle, and Y. Vaisbourd, “First order methods beyond convexity and Lipschitz gradient continuity with applications to quadratic inverse problems,” SIAM Journal on Optimization, vol. 28, no. 3, pp. 2131–2151, 2018.
  40. X.-J. Cai, K. Guo, F. Jiang, K. Wang, Z.-M. Wu, and D.-R. Han, “The developments of proximal point algorithms,” Journal of the Operations Research Society of China, vol. 10, no. 2, pp. 197–239, 2022.
  41. H. He and Z. Zhang, “A unified Bregman alternating minimization algorithm for generalized DC programming with applications to image processing,” arXiv preprint arXiv:2209.07323, 2022.
  42. Z. Wu, C. Li, M. Li, and A. Lim, “Inertial proximal gradient methods with Bregman regularization for a class of nonconvex optimization problems,” Journal of Global Optimization, vol. 79, pp. 617–644, 2021.
  43. J. Li, F. Fang, K. Mei, and G. Zhang, “Multi-scale residual network for image super-resolution,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 517–532.
  44. X. Gao, X. Cai, and D. Han, “A gauss–seidel type inertial proximal alternating linearized minimization for a class of nonconvex optimization problems,” Journal of Global Optimization, vol. 76, pp. 863–887, 2020.
  45. C. Guo and J. Zhao, “Two-step inertial Bregman proximal alternating linearized minimization algorithm for nonconvex and nonsmooth problems,” arXiv preprint arXiv:2306.07614, 2023.
  46. M. C. Mukkamala, P. Ochs, T. Pock, and S. Sabach, “Convex-concave backtracking for inertial Bregman proximal gradient algorithms in nonconvex optimization,” SIAM Journal on Mathematics of Data Science, vol. 2, no. 3, pp. 658–682, 2020.
  47. T. Pock and S. Sabach, “Inertial proximal alternating linearized minimization (iPALMss) for nonconvex and nonsmooth problems,” SIAM Journal on Imaging Sciences, vol. 9, no. 4, pp. 1756–1787, 2016.
  48. A. Chambolle, “An algorithm for total variation minimization and applications,” Journal of Mathematical Imaging and Vision, vol. 20, pp. 89–97, 2004.
  49. J. Rim, H. Lee, J. Won, and S. Cho, “Real-world blur dataset for learning and benchmarking deblurring algorithms,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV 16.   Springer, 2020, pp. 184–201.
  50. C. Huang, Y. Fang, T. Wu, T. Zeng, and Y. Zeng, “Quaternion screened Poisson equation for low-light image enhancement,” IEEE Signal Processing Letters, vol. 29, pp. 1417–1421, 2022.
  51. C. Liu, F. Wu, and X. Wang, “Efinet: Restoration for low-light images via enhancement-fusion iterative network,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 12, pp. 8486–8499, 2022.
  52. 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 Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 12 140–12 149.
  53. X. Guo and Q. Hu, “Low-light image enhancement via breaking down the darkness,” International Journal of Computer Vision, vol. 131, no. 1, pp. 48–66, 2023.
  54. C. Lee, C. Lee, and C.-S. Kim, “Contrast enhancement based on layered difference representation of 2D histograms,” IEEE Transactions on Image Processing, vol. 22, no. 12, pp. 5372–5384, 2013.
  55. X. Guo, Y. Li, and H. Ling, “LIME: Low-light image enhancement via illumination map estimation,” IEEE Transactions on Image Processing, vol. 26, no. 2, pp. 982–993, 2016.
  56. K. Ma, K. Zeng, and Z. Wang, “Perceptual quality assessment for multi-exposure image fusion,” IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 3345–3356, 2015.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now