Abstract
It is the age of social media and influencer culture and the importance of style and aesthetic has never been more apparent. Photo-retouching remains a critical and often, time consuming part of this process. To simplify the complex and skillful task of retouching, this paper proposes a Deep Learning based automatic photo retouching solution. It builds upon a GAN-based architecture, trained in an unsupervised manner to instantly enhance images. However, most Deep Learning based approaches are black-boxes and provide the user little to no insight into the enhancements applied, leaving it difficult to perform minor tweaking in enhancement as per preference. Hence, we also propose an algorithm to estimate parametric modifications given a pair of images with the aim of enabling the user more in the process of image enhancement. Together these allow complete transparency in deep learning based image enhancement while still producing results comparable to black-box approaches. We demonstrate the effectiveness of the proposed solution by comparing Mean Opinion Scores (MoS) and show that more than 84% of the users prefer the proposed solution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yuanming, H., et al.: Exposure: a white-box photo post-processing framework. ACM Trans. Graph. (TOG). 37(2), 26 (2018)
Gharbi, M., et al.: Deep bilateral learning for real-time image enhancement. ACM Trans. Graph. (TOG) 36(4), 118 (2017)
Bianco, S., Cusano, C., Piccoli, F., Schettini, R.: Learning parametric functions for color image enhancement. In: Tominaga, S., Schettini, R., Trémeau, A., Horiuchi, T. (eds.) CCIW 2019. LNCS, vol. 11418, pp. 209–220. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-13940-7_16
Zhu, J.Y., et al.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Chong, N., Wong, L., See, J.: GANmera: reproducing aesthetically pleasing photographs using deep adversarial networks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA, pp. 2179–2187 (2019)
Deng, Y., et al.: Aesthetic-driven image enhancement by adversarial learning. In: ACM Multimedia (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS) 27 (2014)
Chen, Y., et al.: Deep photo enhancer: unpaired learning for image enhancement from photographs with GANs. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, pp. 6306–6314 (2018)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. arXiv preprint arXiv:1701.07875 (2017)
Talebi, H., Milanfar, P.: NIMA: neural image assessment. IEEE Trans. Image Process. 27(8), 3998–4011 (2018)
Bychkovsky, V., et al.: Learning photographic global tonal adjustment with a database of input/output image pairs. In: The Twenty-Fourth IEEE Conference on Computer Vision and Pattern Recognition (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sharma, M., Mittar, R., Chakraborty, P. (2021). Deep Learning Based Image Enhancement and Black Box Filter Parameter Estimation. In: Singh, S.K., Roy, P., Raman, B., Nagabhushan, P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1377. Springer, Singapore. https://doi.org/10.1007/978-981-16-1092-9_15
Download citation
DOI: https://doi.org/10.1007/978-981-16-1092-9_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1091-2
Online ISBN: 978-981-16-1092-9
eBook Packages: Computer ScienceComputer Science (R0)