Image Enhancement Based on Light-Curve and Color Decoupling Techniques

Chengyu Liang

doi:10.62051/ijcsit.v4n2.05

Authors

Chengyu Liang

DOI:

https://doi.org/10.62051/ijcsit.v4n2.05

Keywords:

HSV color-model, Luminance curve, Purkinje effect, Color decoupling

Abstract

This paper presents a lightweight, unsupervised image enhancement method based on existing models, termed LCCDnet (Light-curve and Color-decoupled). The method separates the enhancement task into light enhancement and detail optimization. Images are decomposed into HSV channels: HS channels manage image details, while the V channel controls brightness. A light curve is applied to estimate brightness enhancement, with design considerations for pixel value range, monotonicity, and differentiability. For HS channels, a method inspired by the Purkinje effect decomposes the channel into two intrinsic color values, which are then combined into a novel HS channel. LCCDnet does not require paired or unpaired data for training. The method achieves image enhancement through intuitive nonlinear curve mapping, focusing on image details. It is computationally efficient and requires minimal training data, showing promising potential despite some limitations in certain scenarios.

Downloads

Download data is not yet available.

References

[1] Wang, R., Zhang, Q., Fu, C. W., Shen, X., Zheng, W. S., & Jia, J. (2019). Underexposed photo enhancement using deep illumination estimation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 6849-6857.

[2] Wei, C., Wang, W., Yang, W., & Liu, J. (2018). Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560.

[3] Jiang, Y., Gong, X., Liu, D., Cheng, Y., Fang, C., Shen, X., ... & Wang, Z. (2021). Enlightengan: Deep light enhancement without paired supervision. IEEE transactions on image processing, 30, 2340-2349.

[4] Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision. pp. 2223-2232.

[5] Coltuc, D., Bolon, P., & Chassery, J. M. (2006). Exact histogram specification. IEEE Transactions on Image processing, 15(5), 1143-1152.

[6] Ibrahim, H., & Kong, N. S. P. (2007). Brightness preserving dynamic histogram equalization for image contrast enhancement. IEEE Transactions on Consumer Electronics, 53(4), 1752-1758.

[7] Lee, C., Lee, C., & Kim, C. S. (2013). Contrast enhancement based on layered difference representation of 2D histograms. IEEE transactions on image processing, 22(12), 5372-5384.

[8] Stark, J. A. (2000). Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on image processing, 9(5), 889-896.

[9] Land, E. H. (1977). The retinex theory of color vision. Scientific american, 237(6), 108-129.

[10] Wang, S., Zheng, J., Hu, H. M., & Li, B. (2013). Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE transactions on image processing, 22(9), 3538-3548.

[11] Fu, X., Zeng, D., Huang, Y., Zhang, X. P., & Ding, X. (2016). A weighted variational model for simultaneous reflectance and illumination estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2782-2790.

[12] Guo, X., Li, Y., & Ling, H. (2016). LIME: Low-light image enhancement via illumination map estimation. IEEE Transactions on image processing, 26(2), 982-993.

[13] Li, M., Liu, J., Yang, W., Sun, X., & Guo, Z. (2018). Structure-revealing low-light image enhancement via robust retinex model. IEEE Transactions on Image Processing, 27(6), 2828-2841.

[14] Guo, C., Li, C., Guo, J., Loy, C. C., Hou, J., Kwong, S., & Cong, R. (2020). Zero-reference deep curve estimation for low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 1780-1789.

[15] Zhang, Y., Di, X., Wu, J., Fu, R., Li, Y., Wang, Y., ... & Wang, C. (2023). Simplifying low-light image enhancement networks with relative loss functions. arXiv preprint arXiv:2304.02978.

[16] Feng, Y., Zhang, C., Wang, P., Wu, P., Yan, Q., & Zhang, Y. (2024). You only need one color space: An efficient network for low-light image enhancement. arXiv preprint arXiv:2402.05809.

[17] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.