Date Log
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Grayscale Image Colorization Based on Semantic Segmentation
Corresponding Author(s) : VIORICA PUȘCAȘ
Student Thinkers and Advanced Research,
Vol. 3 No. 1 (2024): Proceedings of the 7th International Conference XGEN
Abstract
Colorizing grayscale images is a prominent challenge in Computer Vision, with numerous deep learning approaches being prevalent in the literature for this task. This paper introduces a multi-head fully convolutional network architecture, taking grayscale images as input and outputting the chromaticity information for colorization and segmentation masks for semantic segmentation. The model is inspired by the one proposed by Iizuka et al. in "Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification" (2016), but goes a step further by transitioning from iconic images to images with a number of different object categories. Preliminary empirical results, measured on both subjective and objective scales, demonstrate convincing colorization, without artifacts or color bleeding.
Keywords
Download Citation
Endnote/Zotero/Mendeley (RIS)BibTeX
- S. Iizuka, E. Simo-Serra și H. Ishikawa, „Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification,” ACM Transactions on Graphics (ToG), vol. 35, nr. 4, pp. 1-11, 2016.
- R. Zhang, P. Isola și A. A. Efros, „Colorful image colorization,” în Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, 2016.
- G. Larsson, M. Maire și G. Shakhnarovich, „Learning representations for automatic colorization,” în Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part IV 14, 2016.
- X. Kuang, J. Zhu, X. Sui, Y. Liu, C. Liu, Q. Chen și G. Gu, „Thermal infrared colorization via conditional generative adversarial network,” Infrared Physics & Technology, vol. 107, p. 103338, 2020.
- P. L. Suárez, A. D. Sappa și B. X. Vintimilla, „Infrared image colorization based on a triplet DCGAN architecture,” în Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017.
- O. Ronneberger, P. Fischer și T. Brox, „U-net: Convolutional networks for biomedical image segmentation,” în Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, 2015.
- T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár și C. L. Zitnick, „Microsoft COCO: Common Objects in Context,” în Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, 2014.
- Ultralytics, „YOLOv8: A New State-of-the-Art Computer Vision Model,” [Interactiv]. Available: https://yolov8.com. [Accesat 18 mai 2024].
References
S. Iizuka, E. Simo-Serra și H. Ishikawa, „Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification,” ACM Transactions on Graphics (ToG), vol. 35, nr. 4, pp. 1-11, 2016.
R. Zhang, P. Isola și A. A. Efros, „Colorful image colorization,” în Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, 2016.
G. Larsson, M. Maire și G. Shakhnarovich, „Learning representations for automatic colorization,” în Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part IV 14, 2016.
X. Kuang, J. Zhu, X. Sui, Y. Liu, C. Liu, Q. Chen și G. Gu, „Thermal infrared colorization via conditional generative adversarial network,” Infrared Physics & Technology, vol. 107, p. 103338, 2020.
P. L. Suárez, A. D. Sappa și B. X. Vintimilla, „Infrared image colorization based on a triplet DCGAN architecture,” în Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017.
O. Ronneberger, P. Fischer și T. Brox, „U-net: Convolutional networks for biomedical image segmentation,” în Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, 2015.
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár și C. L. Zitnick, „Microsoft COCO: Common Objects in Context,” în Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, 2014.
Ultralytics, „YOLOv8: A New State-of-the-Art Computer Vision Model,” [Interactiv]. Available: https://yolov8.com. [Accesat 18 mai 2024].