GAN-Based Local Lightness-Aware Enhancement Network for Underexposed Images
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficientconsideration during enhancement procedure will result in over-/under-exposure, loss of details and colordistortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed inthis paper based on the guidance of the unpaired low-/normal-light images. The key components in our networkinclude super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), anddenoising-scaling module (DSM). The SRM improves the resolution of the low-light input images beforeillumination enhancement. Such design philosophy improves the effectiveness of texture details preservationby operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectivelydistinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistencyof illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, localregion 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 humanaesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Bothqualitative and quantitative experiments demonstrate that our approach achieves favorable results, whichindicates its superior capacity on illumination and texture details restoration.
Abstract
Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficientconsideration during enhancement procedure will result in over-/under-exposure, loss of details and colordistortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed inthis paper based on the guidance of the unpaired low-/normal-light images. The key components in our networkinclude super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), anddenoising-scaling module (DSM). The SRM improves the resolution of the low-light input images beforeillumination enhancement. Such design philosophy improves the effectiveness of texture details preservationby operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectivelydistinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistencyof illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, localregion 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 humanaesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Bothqualitative and quantitative experiments demonstrate that our approach achieves favorable results, whichindicates its superior capacity on illumination and texture details restoration.
참고문헌 (22)
- Zhonghua Wang, "A New Image Enhancement Algorithm Based on Bidirectional Diffusion", JIPS(Journal of Information Processing Systems), 16(1), pp.49~60 (2020), 한국정보처리학회[DOI]
- H. Ibrahim, "Brightness preserving dynamic histogram equalization for image contrast enhancement", IEEE Transactions on Consumer Electronics, 53(4), pp.1752~1758 (2007)
- Y. Zhang, "Beyond brightening low-light images", International Journal of Computer Vision, 129, pp.1013~1037 (2021)
- K. G. Lore, "LLNet : a deep autoencoder approach to natural low-light image enhancement", Pattern Recognition, 61, pp.650~662 (2017)
- F. Lv, "Attention guided low-light image enhancement with a large scale low-light simulation dataset", International Journal of Computer Vision, 129, pp.2175~2193 (2021)
- S. Lim, "DSLR : deep stacked Laplacian restorer for low-light image enhancement", IEEE Transactions on Multimedia, 23, pp.4272~4284 (2021)
- Liquan Zhao, "A Multi-Scale U-Shaped Attention Network-Based GAN Method for Single Image Dehazing", Human-centric Computing and Information Sciences, 11(0), pp.1~1 (2021), KIPS-CSWRG[DOI]
- X. Gao, "Quality elevation technique for UHD video and its VLSI solution", Journal of Chongqing University of Posts and Telecommunications : Natural Science Edition, 32(5), pp.681~697 (2020)
- Y. Jiang, "EnlightenGAN : deep light enhancement without paired supervision", IEEE Transactions on Image Processing, 30, pp.2340~2349 (2021)
- X. Xu, "Image deblurring with blur kernel estimation in RGB channels", Journal of Chongqing University of Posts and Telecommunications : Natural Science Edition, 30(2), pp.216~221 (2018)
- B. Lim, "Enhanced deep residual networks for single image superresolution", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.1132~1140 (2017)
- J. Hu, "Squeeze-and-excitation networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.7132~7141 (2018)
- S. Woo, "CBAM: convolutional block attention module", Proceedings of the European Conference on Computer Vision (ECCV), pp.3~19 (2018)
- X. Mao, "Least squares generative adversarial networks", Proceedings of the IEEE International Conference on Computer Vision, pp.2813~2821 (2017)
- M. Zhang, "A new referenceless image quality index to evaluate denoising performance of SAR images", Journal of Chongqing University of Posts and Telecommunications : Natural Science Edition, 30(4), pp.530~536 (2018)
- S. Guo, "Toward convolutional blind denoising of real photographs", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1712~1722 (2019)
- Y. P. Loh, "Getting to know low-light images with the exclusively dark dataset", Computer Vision and Image Understanding, 178, pp.30~42 (2019)
- "Deep Retinex decomposition for low-light enhancement" (2018)[URL]
- D. T. Dang-Nguyen, "RAISE: a raw images dataset for digital image forensics", Proceedings of the 6th ACM Multimedia Systems Conference, pp.219~224 (2015)
- A. Zhu, "Zero-shot restoration of underexposed images via robust retinex decomposition", Proceedings of 2020 IEEE International Conference on Multimedia and Expo (ICME), pp.1~6 (2020)
- A. Mittal, "Making a"completely blind"image quality analyzer", IEEE Signal Processing Letters, 20(3), pp.209~212 (2013)
- W. Yang, "From fidelity to perceptual quality : a semi-supervised approach for low-light image enhancement", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3060~3069 (2020)