Abstract
Mobile Cameras capture images deftly in scenarios with ample light and can meticulously highlight even the finest detail from the visible spectrum. However, they perform poorly in low-light setups owing to their sensor size, and so, a flash gets triggered to capture the image better. Photographs taken using a flashlight have artefacts like atypical skin tone, sharp shadow, non-uniform illumination, and specular highlights. This work proposes a conditional generative adversarial network (cGAN) to generate ambient images with uniform illumination from the flash photographs and mitigate other artefacts introduced by the triggered flash. The proposed architecture’s generator has a VGG-16 inspired encoder at its core, pipelined with a decoder. A discriminator is employed to classify patches from each image as real or generated and penalize the network accordingly. Experimental results demonstrate that the proposed architecture significantly outperforms the current state-of-the-art, performing even better on facial images with homogenous backgrounds.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chávez, J., Mora, R., Cayllahua-Cahuina, E.: Ambient lighting generation for flash images with guided conditional adversarial networks. arXiv preprint arXiv:1912.08813 (2019)
Capece, N., Banterle, F., Cignoni, P., Ganovelli, F., Scopigno, R., Erra, U.: DeepFlash: turning a flash selfie into a studio portrait. Sig. Process. Image Commun. 77, 28–39 (2019)
Aksoy, Y., et al.: A dataset of flash and ambient illumination pairs from the crowd. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 644–660. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_39
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)
Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)
Ke, Z., Sun, J., Li, K., Yan, Q., Lau, R.W.: MODNet: real-time trimap-free portrait matting via objective decomposition. In: AAAI (2022)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
Elad, M.: On the origin of the bilateral filter and ways to improve it. IEEE Trans. Image Process. 11(10), 1141–1151 (2002)
Zhou, S., Nie, D., Adeli, E., Yin, J., Lian, J., Shen, D.: High-resolution encoder-decoder networks for low-contrast medical image segmentation. IEEE Trans. Image Process. 29, 461–475 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Li, C., Wand, M.: Precomputed real-time texture synthesis with Markovian generative adversarial networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 702–716. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_43
Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition, pp. 2366–2369. IEEE, August 2010
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wasi, A., Bhinder, I.S., Jeba Shiney, O., Prabhu, M.K., Ramesh Kumar, L. (2023). FlashGAN: Generating Ambient Images from Flash Photographs. In: Gupta, D., Bhurchandi, K., Murala, S., Raman, B., Kumar, S. (eds) Computer Vision and Image Processing. CVIP 2022. Communications in Computer and Information Science, vol 1776. Springer, Cham. https://doi.org/10.1007/978-3-031-31407-0_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-31407-0_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31406-3
Online ISBN: 978-3-031-31407-0
eBook Packages: Computer ScienceComputer Science (R0)