Journal of Information Processing Systems

  • 제18권4호
  • /
  • Pages.575-586
  • /
  • 2022
  • /
  • 1976-913X(pISSN)
  • /
  • 2092-805X(eISSN)
한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

GAN-Based Local Lightness-Aware Enhancement Network for Underexposed Images

  • Chen, Yong (School of Automation, Chongqing University of Posts and Telecommunications) ;
  • Huang, Meiyong (School of Automation, Chongqing University of Posts and Telecommunications) ;
  • Liu, Huanlin (School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications) ;
  • Zhang, Jinliang (School of Automation, Chongqing University of Posts and Telecommunications) ;
  • Shao, Kaixin (School of Automation, Chongqing University of Posts and Telecommunications)
  • 투고 : 2022.01.27
  • 심사 : 2022.07.21
  • 발행 : 2022.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficient consideration during enhancement procedure will result in over-/under-exposure, loss of details and color distortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed in this paper based on the guidance of the unpaired low-/normal-light images. The key components in our network include super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), and denoising-scaling module (DSM). The SRM improves the resolution of the low-light input images before illumination enhancement. Such design philosophy improves the effectiveness of texture details preservation by operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectively distinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistency of illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, local region discriminator, and color discriminator performs assessment from different perspectives to avoid over-/under-exposure and color distortion, which guides the network to generate images that in line with human aesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Both qualitative and quantitative experiments demonstrate that our approach achieves favorable results, which indicates its superior capacity on illumination and texture details restoration.

키워드

과제정보

The research was funded by the Chongqing Education Committee Science Foundation of China (No. KJ130529).

참고문헌

  1. Z. Wang, X. Huang, and F. Huang, "A new image enhancement algorithm based on bidirectional diffusion," Journal of Information Processing Systems, vol. 16, no. 1, pp. 49-60, 2020. https://doi.org/10.3745/JIPS.04.0155
  2. H. Ibrahim and N. S. P. Kong, "Brightness preserving dynamic histogram equalization for image contrast enhancement," IEEE Transactions on Consumer Electronics, vol. 53, no. 4, pp. 1752-1758, 2007. https://doi.org/10.1109/TCE.2007.4429280
  3. Y. Zhang, X. Guo, J. Ma, W. Liu, and J. Zhang, "Beyond brightening low-light images," International Journal of Computer Vision, vol. 129, pp. 1013-1037, 2021. https://doi.org/10.1007/s11263-020-01407-x
  4. K. G. Lore, A. Akintayo, and S. Sarkar, "LLNet: a deep autoencoder approach to natural low-light image enhancement," Pattern Recognition, vol. 61, pp. 650-662, 2017. https://doi.org/10.1016/j.patcog.2016.06.008
  5. F. Lv, Y. Li, and F. Lu, "Attention guided low-light image enhancement with a large scale low-light simulation dataset," International Journal of Computer Vision, vol. 129, pp. 2175-2193, 2021. https://doi.org/10.1007/s11263-021-01466-8
  6. S. Lim and W. Kim, "DSLR: deep stacked Laplacian restorer for low-light image enhancement," IEEE Transactions on Multimedia, vol. 23, pp. 4272-4284, 2021. https://doi.org/10.1109/TMM.2020.3039361
  7. L. Zhao, Y. Zhang, and Y. Cui, "A multi-scale U-shaped attention network-based GAN method for single image dehazing," Human-centric Computing and Information Sciences, vol. 11, article no. 38, pp. 562-578, 2021. https://doi.org/10.22967/HCIS.2021.11.038
  8. X. Gao, W. Lu, L. Zha, Z. Hui, T. Qi, and J. Jiang, "Quality elevation technique for UHD video and its VLSI solution," Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, vol. 32, no. 5, pp. 681-697, 2020.
  9. 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 Transactions on Image Processing, vol. 30, pp. 2340-2349, 2021. https://doi.org/10.1109/TIP.2021.3051462
  10. X. Xu, H. Liu, Y. Li, and Y. Zhou, "Image deblurring with blur kernel estimation in RGB channels," Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, vol. 30, no. 2, pp. 216-221, 2018.
  11. B. Lim, S. Son, H. Kim, S. Nah, and K. M. Lee, "Enhanced deep residual networks for single image superresolution," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, 2017, pp. 1132-1140.
  12. J. Hu, L. Shen, and G. Sun, "Squeeze-and-excitation networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 7132-7141.
  13. S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, "CBAM: convolutional block attention module," in Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 2018, pp. 3-19.
  14. X. Mao, Q. Li, H. Xie, R. Y. Lau, Z. Wang, and S. Paul Smolley, "Least squares generative adversarial networks," in Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 2017, pp. 2813-2821.
  15. M. Zhang and J. Yang, "A new referenceless image quality index to evaluate denoising performance of SAR images," Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, vol. 30, no. 4, pp. 530-536, 2018.
  16. S. Guo, Z. Yan, K. Zhang, W. Zuo, and L. Zhang, "Toward convolutional blind denoising of real photographs," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, 2019, pp. 1712-1722.
  17. Y. P. Loh and C. S. Chan, "Getting to know low-light images with the exclusively dark dataset," Computer Vision and Image Understanding, vol. 178, pp. 30-42, 2019. https://doi.org/10.1016/j.cviu.2018.10.010
  18. C. Wei, W. Wang, W. Yang, and J. Liu, "Deep Retinex decomposition for low-light enhancement," 2018 [Online]. Available: https://arxiv.org/abs/1808.04560.
  19. D. T. Dang-Nguyen, C. Pasquini, V. Conotter, and G. Boato, "RAISE: a raw images dataset for digital image forensics," in Proceedings of the 6th ACM Multimedia Systems Conference, Portland, OR, 2015, pp. 219-224.
  20. A. Zhu, L. Zhang, Y. Shen, Y. Ma, S. Zhao, and Y. Zhou, "Zero-shot restoration of underexposed images via robust retinex decomposition," in Proceedings of 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK, 2020, pp. 1-6.
  21. A. Mittal, R. Soundararajan, and A. C. Bovik, "Making a "completely blind" image quality analyzer," IEEE Signal Processing Letters, vol. 20, no. 3, pp. 209-212, 2013. https://doi.org/10.1109/LSP.2012.2227726
  22. W. Yang, S. Wang, Y. Fang, Y. Wang, and J. Liu, "From fidelity to perceptual quality: a semi-supervised approach for low-light image enhancement," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, 2020, pp. 3060-3069.