Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement (2404.03327v1)

Published 4 Apr 2024 in cs.CV and eess.IV

Abstract: Many existing methods for low-light image enhancement (LLIE) based on Retinex theory ignore important factors that affect the validity of this theory in digital imaging, such as noise, quantization error, non-linearity, and dynamic range overflow. In this paper, we propose a new expression called Digital-Imaging Retinex theory (DI-Retinex) through theoretical and experimental analysis of Retinex theory in digital imaging. Our new expression includes an offset term in the enhancement model, which allows for pixel-wise brightness contrast adjustment with a non-linear mapping function. In addition, to solve the lowlight enhancement problem in an unsupervised manner, we propose an image-adaptive masked reverse degradation loss in Gamma space. We also design a variance suppression loss for regulating the additional offset term. Extensive experiments show that our proposed method outperforms all existing unsupervised methods in terms of visual quality, model size, and speed. Our algorithm can also assist downstream face detectors in low-light, as it shows the most performance gain after the low-light enhancement compared to other methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (95)
  1. A dynamic histogram equalization for image contrast enhancement. IEEE Transactions on Consumer Electronics, 53(2):593–600, 2007.
  2. An intensity similarity measure in low-light conditions. In European Conference on Computer Vision, pages 267–280. Springer, 2006.
  3. android gpuimage. Source code for gpuimagecontrastfilter. [EB/OL]. https://github.com/cats-oss/android-gpuimage/blob/master/library/src/main/java/jp/co/cyberagent/android/gpuimage/filter/.
  4. 1/f noise and extreme value statistics. Physical review letters, 87(24):240601, 2001.
  5. Advanced high dynamic range imaging: Theory and practice,(2011).
  6. Y. M. Blanter and M. Büttiker. Shot noise in mesoscopic conductors. Physics reports, 336(1-2):1–166, 2000.
  7. A joint intrinsic-extrinsic prior model for retinex. In Proceedings of the IEEE international conference on computer vision, pages 4000–4009, 2017.
  8. Learning a deep single image contrast enhancer from multi-exposure images. IEEE Transactions on Image Processing, 27(4):2049–2062, 2018.
  9. Retinexformer: One-stage retinex-based transformer for low-light image enhancement. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 12504–12513, October 2023.
  10. Learning to see in the dark. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3291–3300, 2018.
  11. Seeing motion in the dark. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3185–3194, 2019.
  12. Exact histogram specification. IEEE Transactions on Image processing, 15(5):1143–1152, 2006.
  13. Fast efficient algorithm for enhancement of low lighting video. In ACM SIGGRAPH 2010 Posters, pages 1–1. 2010.
  14. Integrating semantic segmentation and retinex model for low-light image enhancement. In Proceedings of the 28th ACM international conference on multimedia, pages 2317–2325, 2020.
  15. A. C. Fredrik Lundh and Contributors. Source code for pil.imageenhance. [EB/OL]. https://pillow.readthedocs.io/en/stable/_modules/PIL/ImageEnhance.html#Contrast.
  16. You do not need additional priors or regularizers in retinex-based low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 18125–18134, June 2023a.
  17. Retinex-based perceptual contrast enhancement in images using luminance adaptation. IEEE Access, 6:61277–61286, 2018.
  18. A novel retinex based approach for image enhancement with illumination adjustment. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1190–1194. IEEE, 2014.
  19. A fusion-based enhancing method for weakly illuminated images. Signal Processing, 129:82–96, 2016a.
  20. A weighted variational model for simultaneous reflectance and illumination estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2782–2790, 2016b.
  21. Learning a simple low-light image enhancer from paired low-light instances. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22252–22261, 2023b.
  22. Zero-reference deep curve estimation for low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1780–1789, 2020.
  23. Lime: Low-light image enhancement via illumination map estimation. IEEE Transactions on image processing, 26(2):982–993, 2016.
  24. H. A. Haus. Electromagnetic noise and quantum optical measurements. Springer Science & Business Media, 2000.
  25. G. E. Healey and R. Kondepudy. Radiometric ccd camera calibration and noise estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(3):267–276, 1994.
  26. H. Ibrahim and N. S. P. Kong. Brightness preserving dynamic histogram equalization for image contrast enhancement. IEEE Transactions on Consumer Electronics, 53(4):1752–1758, 2007.
  27. J. R. Janesick. Photon transfer. SPIE, 2007.
  28. H. Jiang and Y. Zheng. Learning to see moving objects in the dark. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 7323–7332, 2019. doi: 10.1109/ICCV.2019.00742.
  29. Enlightengan: Deep light enhancement without paired supervision. IEEE Transactions on Image Processing, 30:2340–2349, 2021.
  30. Unsupervised night image enhancement: When layer decomposition meets light-effects suppression. In European Conference on Computer Vision, pages 404–421. Springer, 2022.
  31. A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Transactions on Image processing, 6(7):965–976, 1997a.
  32. Properties and performance of a center/surround retinex. IEEE transactions on image processing, 6(3):451–462, 1997b.
  33. E. H. Land. The retinex theory of color vision. Scientific american, 237(6):108–129, 1977.
  34. Lightness and retinex theory. Josa, 61(1):1–11, 1971.
  35. Contrast enhancement based on layered difference representation of 2d histograms. IEEE transactions on image processing, 22(12):5372–5384, 2013a.
  36. Adaptive multiscale retinex for image contrast enhancement. In 2013 International Conference on Signal-Image Technology & Internet-Based Systems, pages 43–50. IEEE, 2013b.
  37. Lightennet: A convolutional neural network for weakly illuminated image enhancement. Pattern recognition letters, 104:15–22, 2018a.
  38. Low-light image and video enhancement using deep learning: A survey. IEEE Transactions on Pattern Analysis & Machine Intelligence, (01):1–1, 2021a.
  39. Learning to enhance low-light image via zero-reference deep curve estimation. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021b. doi: 10.1109/TPAMI.2021.3063604.
  40. Dsfd: Dual shot face detector. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019.
  41. A low-light image enhancement method for both denoising and contrast enlarging. In 2015 IEEE international conference on image processing (ICIP), pages 3730–3734. IEEE, 2015.
  42. Structure-revealing low-light image enhancement via robust retinex model. IEEE Transactions on Image Processing, 27(6):2828–2841, 2018b.
  43. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10561–10570, 2021.
  44. Learning with nested scene modeling and cooperative architecture search for low-light vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5):5953–5969, 2022.
  45. Llnet: A deep autoencoder approach to natural low-light image enhancement. Pattern Recognition, 61:650–662, 2017.
  46. Mbllen: Low-light image/video enhancement using cnns. In BMVC, volume 220, page 4, 2018.
  47. Toward fast, flexible, and robust low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5637–5646, 2022.
  48. Subelectron read noise at mhz pixel rates. In Sensors and Camera Systems for Scientific, Industrial, and Digital Photography Applications II, volume 4306, pages 289–298. SPIE, 2001.
  49. S. Mann and R. Picard. Beingundigital’with digital cameras. MIT Media Lab Perceptual, 1:2, 1994.
  50. Exposure fusion. In 15th Pacific Conference on Computer Graphics and Applications (PG’07), pages 382–390. IEEE, 2007.
  51. Exposure fusion: A simple and practical alternative to high dynamic range photography. In Computer graphics forum, volume 28, pages 161–171. Wiley Online Library, 2009.
  52. T. Mitsunaga and S. K. Nayar. Radiometric self calibration. In Proceedings. 1999 IEEE computer society conference on computer vision and pattern recognition (Cat. No PR00149), volume 1, pages 374–380. IEEE, 1999.
  53. Application of plasma-doping (plad) technique to reduce dark current of cmos image sensors. IEEE electron device letters, 28(2):114–116, 2007.
  54. V. Padmavathy and R. Priya. Image contrast enhancement techniques-a survey. International Journal of Engineering & Technology, 7(2.33):466–469, 2018.
  55. Contrast enhancement for low-light image enhancement: A survey. IEIE Transactions on Smart Processing and Computing, 7:36–48, 2018.
  56. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  57. S. M. Pizer. Contrast-limited adaptive histogram equalization: Speed and effectiveness stephen m. pizer, r. eugene johnston, james p. ericksen, bonnie c. yankaskas, keith e. muller medical image display research group. In Proceedings of the first conference on visualization in biomedical computing, Atlanta, Georgia, volume 337, page 1, 1990.
  58. Low-light image enhancement via a deep hybrid network. IEEE Transactions on Image Processing, 28(9):4364–4375, 2019.
  59. Joint enhancement and denoising method via sequential decomposition. In 2018 IEEE international symposium on circuits and systems (ISCAS), pages 1–5. IEEE, 2018.
  60. W. Schottky. Über spontane stromschwankungen in verschiedenen elektrizitätsleitern. Annalen der physik, 362(23):541–567, 1918.
  61. J. A. Stark. Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on image processing, 9(5):889–896, 2000.
  62. A comprehensive survey on image contrast enhancement techniques in spatial domain. Sensing and Imaging, 21(1):1–40, 2020.
  63. Variational bayesian method for retinex. IEEE Transactions on Image Processing, 23(8):3381–3396, 2014.
  64. Lightening network for low-light image enhancement. IEEE Transactions on Image Processing, 29:7984–7996, 2020.
  65. Underexposed photo enhancement using deep illumination estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6849–6857, 2019a.
  66. Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE transactions on image processing, 22(9):3538–3548, 2013.
  67. Progressive retinex: Mutually reinforced illumination-noise perception network for low-light image enhancement. In Proceedings of the 27th ACM international conference on multimedia, pages 2015–2023, 2019b.
  68. Low-light image enhancement with normalizing flow. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 2604–2612, 2022.
  69. Low-light image enhancement with illumination-aware gamma correction and complete image modelling network. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 13128–13137, October 2023a.
  70. Exposurediffusion: Learning to expose for low-light image enhancement. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 12438–12448, October 2023b.
  71. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.
  72. E. H. Weber. De Pulsu, resorptione, auditu et tactu: Annotationes anatomicae et physiologicae… CF Koehler, 1831.
  73. Deep retinex decomposition for low-light enhancement. In British Machine Vision Conference, 2018.
  74. 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, pages 5901–5910, 2022.
  75. Learning semantic-aware knowledge guidance for low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1662–1671, June 2023.
  76. Star: A structure and texture aware retinex model. IEEE Transactions on Image Processing, 29:5022–5037, 2020a.
  77. Learning to restore low-light images via decomposition-and-enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2281–2290, 2020b.
  78. Snr-aware low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17714–17724, 2022.
  79. Low-light image enhancement via structure modeling and guidance. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9893–9903, June 2023.
  80. Wider face: A face detection benchmark. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5525–5533, 2016.
  81. From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3063–3072, 2020.
  82. Band representation-based semi-supervised low-light image enhancement: Bridging the gap between signal fidelity and perceptual quality. IEEE Transactions on Image Processing, 30:3461–3473, 2021a.
  83. Sparse gradient regularized deep retinex network for robust low-light image enhancement. IEEE Transactions on Image Processing, 30:2072–2086, 2021b.
  84. Diff-retinex: Rethinking low-light image enhancement with a generative diffusion model. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 12302–12311, October 2023.
  85. A new low-light image enhancement algorithm using camera response model. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 3015–3022, 2017.
  86. L. Yuan and J. Sun. Automatic exposure correction of consumer photographs. In European Conference on Computer Vision, pages 771–785. Springer, 2012.
  87. Ug 2+limit-from2{}^{2+}start_FLOATSUPERSCRIPT 2 + end_FLOATSUPERSCRIPT track 2: A collective benchmark effort for evaluating and advancing image understanding in poor visibility environments. arXiv preprint arXiv:1904.04474, 2019.
  88. Learning temporal consistency for low light video enhancement from single images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4967–4976, 2021.
  89. Zero-shot restoration of back-lit images using deep internal learning. In Proceedings of the 27th ACM International Conference on Multimedia, pages 1623–1631, 2019a.
  90. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018.
  91. Kindling the darkness: A practical low-light image enhancer. In Proceedings of the 27th ACM international conference on multimedia, pages 1632–1640, 2019b.
  92. Deep color consistent network for low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1899–1908, 2022.
  93. Retinexdip: A unified deep framework for low-light image enhancement. IEEE Transactions on Circuits and Systems for Video Technology, 32(3):1076–1088, 2021.
  94. Zero-shot restoration of underexposed images via robust retinex decomposition. In 2020 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE, 2020a.
  95. Eemefn: Low-light image enhancement via edge-enhanced multi-exposure fusion network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 13106–13113, 2020b.
Citations (2)
View on Semantic Scholar

Summary

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

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