Enhanced Tone Mapping Using Regional Fused GAN Training with a Gamma-Shift Dataset
Source abstract
Abstract
High-dynamic-range (HDR) imaging is a digital image processing technique that enhances an image’s visibility by modifying its color and contrast ranges. Generative adversarial networks (GANs) have proven to be potent deep learning models for HDR imaging. However, obtaining a sufficient volume of training image pairs is difficult. This problem has been solved using CycleGAN, but the result of the use of CycleGAN for converting a low-dynamic-range (LDR) image to an HDR image exhibits problematic color distortion, and the intensity of the output image only slightly changes. Therefore, we propose a GAN training optimization model for converting LDR images into HDR images. First, a gamma shift method is proposed for training the GAN model with an extended luminance range. Next, a weighted loss map trains the GAN model for tone compression in the local area of images. Then, a regional fusion training model is used to balance the training method with the regional weight map and the restoring speed of local tone training. Finally, because the generated module tends to show a good performance in bright images, mean gamma tuning is used to evaluate image luminance channels, which are then fed into modules. Tests are conducted on foggy, dark surrounding, bright surrounding, and high-contrast images. The proposed model outperforms conventional models in a comparison test. The proposed model complements the performance of an object detection model even in a real night environment. The model can be used in commercial closed-circuit television surveillance systems and the security industry.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Advanced Image Processing Techniques · Image and Signal Denoising Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic and Electrical Engineering, Kyungpook National University, 80 Deahakro, Buk-Gu, Daegu 702-701, Korea
Funding
the Basic Science Research Program through the National Research Foundation of Korea (NRF) · the BK21 FOUR project funded by the Ministry of Education, Korea
References (32)
Show source-provided references
1. Debevec, P.E., and Malik, J. (2008, January 11–15). Recovering high dynamic range radiance maps from photographs. Proceedings of the ACM SIGGRAPH 2008 Classes on-SIGGRAPH 2008, Los Angeles, CA, USA.10.1145/1401132.1401174 ↗
2. Radiance map construction based on spatial and intensity correlations between LE and SE images for HDR imaging10.1016/j.jvcir.2016.04.022 ↗
3. Banterle, F., Ledda, P., Debattista, K., and Chalmers, A. (December, January 29). Inverse tone mapping. Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, Kuala Lumpur, Malaysia.
4. Ldr2Hdr: On-the-fly reverse tone mapping of legacy video and photographs10.1145/1276377.1276426 ↗
5. Physiological inverse tone mapping based on retina response10.1007/s00371-013-0875-4 ↗
6. Deep reverse tone mapping10.1145/3130800.3130834 ↗
7. HDR image reconstruction from a single exposure using deep CNNs10.1145/3130800.3130816 ↗
8. ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content10.1111/cgf.13340 ↗
9. Liu, Y.-L., Lai, W.-S., Chen, Y.-S., Kao, Y.-L., Yang, M.-H., Chuang, Y.-Y., and Huang, J.-B. (2020, January 13–19). Single-Image HDR reconstruction by learning to reverse the camera pipeline. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00172 ↗
10. Fast Multi-Scale Structural Patch Decomposition for Multi-Exposure Image Fusion10.1109/TIP.2020.2987133 ↗
11. Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images10.1109/TIP.2018.2794218 ↗
12. Wang, R., Zhang, Q., Fu, C.-W., Shen, X., Zheng, W.-S., and Jia, J. (2019, January 16–20). Underexposed photo enhancement using deep illumination estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00701 ↗
13. Backpropagation Applied to Handwritten Zip Code Recognition10.1162/neco.1989.1.4.541 ↗
14. Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
15. Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.244 ↗
16. iCAM06: A refined image appearance model for HDR image rendering10.1016/j.jvcir.2007.06.003 ↗
17. Jung, S.-W., Son, D.-M., Kwon, H.-J., and Lee, S.-H. (2020, January 19–21). Regional weighted generative adversarial network for LDR to HDR image conversion. Proceedings of the International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Fukuoka, Japan.10.1109/ICAIIC48513.2020.9064984 ↗
18. Generative Adversarial Network Using Weighted Loss Map and Regional Fusion Training for LDR-to-HDR Image Conversion10.1587/transinf.2020EDL0001 ↗
19. Mask R-CNN10.1109/TPAMI.2018.2844175 ↗
20. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
21. Online Driver Distraction Detection Using Long Short-Term Memory10.1109/TITS.2011.2119483 ↗
22. Chen, Y.-S., Wang, Y.-C., Kao, M.-H., and Chuang, Y.-Y. (2018, January 18–22). Deep photo enhancer: Unpaired learning for image enhancement from photographs with GANs. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00660 ↗
23. Let there be color! Joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification10.1145/2897824.2925974 ↗
24. Learning Deep Architectures for AI10.1561/2200000006 ↗
25. Zhang, Y., Tian, Y., Kong, Y., Zhong, B., and Fu, Y. (2018, January 18–22). Residual dense network for image super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00262 ↗
26. Deep residual learning for image steganalysis10.1007/s11042-017-4440-4 ↗
27. (2019, November 11). Retinex Images, Available online: https://dragon.larc.nasa.gov.
28. Fairchild, M.D. (2019, June 06). HDR Dataset. Available online: http://rit-mcsl.org/fairchild//HDR.html.
29. Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality10.1109/TIP.2011.2147325 ↗
30. Wang, Z., Simoncelli, E.P., and Bovik, A.C. (2003, January 9–12). Multi-scale structural similarity for image quality assessment. Proceedings of the Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, USA.
31. HDR-VDP-2: A calibrated visual metric for visibility and quality predictions in all luminance conditions10.1145/2010324.1964935 ↗
32. DN-GAN: Denoising generative adversarial networks for speckle noise reduction in optical coherence tomography images10.1016/j.bspc.2019.101632 ↗