Abstract
Image colorization aims to add color information to a grayscale image in a realistic way. Recent methods mostly rely on deep learning strategies. While learning to automatically colorize an image, one can define well-suited objective functions related to the desired color output. Some of them are based on a specific type of error between the predicted image and ground truth one, while other losses rely on the comparison of perceptual properties. But, is the choice of the objective function that crucial, i.e., does it play an important role in the results? In this chapter, we aim to answer this question by analyzing the impact of the loss function on the estimated colorization results. To that goal, we review the different losses and evaluation metrics that are used in the literature. We then train a baseline network with several of the reviewed objective functions, classic L1 and L2 losses, as well as more complex combinations such as Wasserstein GAN and VGG-based LPIPS loss. Quantitative results show that the models trained with VGG-based LPIPS provide overall slightly better results for most evaluation metrics. Qualitative results exhibit more vivid colors when trained with Wasserstein GAN plus the L2 loss or again with the VGG-based LPIPS. Finally, the convenience of quantitative user studies is also discussed to overcome the difficulty of properly assessing on colorized images, notably for the case of old archive photographs where no ground truth is available.
References
Antic, J.: Deoldify. https://github.com/jantic/DeOldify (2019)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein Generative Adversarial Networks. In: International Conference on Machine Learning, vol 70, pp. 214–223 (2017)
Cao, Y., Zhou, Z., Zhang, W., Yu, Y.: Unsupervised diverse colorization via Generative Adversarial Networks. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 151–166 (2017)
Chen, X., Mishra, N., Rohaninejad, M., Abbeel, P.: Pixelsnail: an improved autoregressive generative model. In: International Conference on Machine Learning, pp. 864–872 (2018)
Cheng, Z., Yang, Q., Sheng, B.: Deep colorization. In: IEEE International Conference on Computer Vision, pp. 415–423 (2015)
Deshpande, A., Lu, J., Yeh, M.-C., Jin Chong, M., Forsyth, D.: Learning diverse image colorization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6837–6845 (2017)
Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Comparison of full-reference image quality models for optimization of image processing systems. Int. J. Comput. Vis. 129(4), 1258–1281 (2021)
Dowson, D., Landau, B.: The Fréchet distance between multivariate normal distributions. J. Multivar. Anal. 12(3), 450–455 (1982)
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. J. Vis. 16(12), 326 (2016)
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (2014)
Guadarrama, S., Dahl, R., Bieber, D., Norouzi, M., Shlens, J., Murphy, K.: Pixcolor: pixel recursive colorization. In: British Machine Vision Conference (2017)
Gu, S., Timofte, R., Zhang, R.: Ntire 2019 challenge on image colorization: report. In: Conference on Computer Vision and Pattern Recognition Workshops (2019)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5769–5779 (2017)
He, M., Chen, D., Liao, J., Sander, P.V., Yuan, L.: Deep exemplar-based colorization. ACM Trans. Graph. 37(4), 1–16 (2018)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Ho, J., Kalchbrenner, N., Weissenborn, D., Salimans, T.: Axial attention in multidimensional transformers (2019). arXiv preprint arXiv:1912.12180
Iizuka, S., Simo-Serra, E., Ishikawa, H.: Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Trans. Graph. 35(4), 1–11 (2016)
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: European Conference on Computer Vision, pp. 694–711 (2016)
Kong, G., Tian, H., Duan, X., Long, H.: Adversarial edge-aware image colorization with semantic segmentation. IEEE Access 9, 28194–28203 (2021)
Kumar, M., Weissenborn, D., Kalchbrenner, N.: Colorization transformer (2021). arXiv preprint arXiv:2102.04432
Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: European Conference on Computer Vision, pp. 577–593 (2016)
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision, pp. 740–755 (2014)
Lübbe, E.: Colours in the Mind-Colour Systems in Reality: A Formula for Colour Saturation. BoD–Books on Demand, Norderstedt (2010)
Mouzon, T., Pierre, F., Berger, M.-O.: Joint CNN and variational model for fully-automatic image colorization. In: Scale Space and Variational Methods in Computer Vision, pp. 535–546 (2019)
Nazeri, K., Ng, E., Ebrahimi, M.: Image colorization using Generative Adversarial Networks. In: International Conference on Articulated Motion and Deformable Objects, pp. 85–94 (2018)
Oord, A.V.D., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., Kavukcuoglu, K.: Conditional image generation with PixelCNN decoders. In: Advances in Neural Information Processing Systems (2016)
Pierre, F., Aujol, J.-F.: Recent approaches for image colorization. In: Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging (2020)
Pierre, F., Aujol, J.-F., Bugeau, A., Papadakis, N., Ta, V.-T.: Luminance-chrominance model for image colorization. SIAM J. Imag. Sci. 8(1), 536–563 (2015)
Pucci, R., Micheloni, C., Martinel, N.: Collaborative image and object level features for image colourisation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2160–2169 (2021)
Riba, E., Mishkin, D., Ponsa, D., Rublee, E., Bradski, G.: Kornia: an open source differentiable computer vision library for PyTorch. In: Winter Conference on Applications of Computer Vision, pp. 3674–3683 (2020)
Royer, A., Kolesnikov, A., Lampert, C.H.: Probabilistic image colorization. In: British Machine Vision Conference (2017)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)
Su, J.-W., Chu, H.-K., Huang, J.-B.: Instance-aware image colorization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7968–7977 (2020)
Van Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747–1756 (2016)
Vitoria, P., Raad, L., Ballester, C.: ChromaGAN: adversarial picture colorization with semantic class distribution. In: Winter Conference on Applications of Computer Vision, pp. 2445–2454 (2020)
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)
Yoo, S., Bahng, H., Chung, S., Lee, J., Chang, J., Choo, J.: Coloring with limited data: few-shot colorization via memory augmented networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)
Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: European Conference on Computer Vision, pp. 649–666 (2016)
Zhang, R., Zhu, J.-Y., Isola, P., Geng, X., Lin, A.S., Yu, T., Efros, A.A.: Real-time user-guided image colorization with learned deep priors. ACM Trans. Graph. 36, 1–11 (2017)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–595 (2018)
Acknowledgements
This study has been carried out with financial support from the French Research Agency through the PostProdLEAP project (ANR-19-CE23-0027-01) and from the EU Horizon 2020 research and innovation programme NoMADS (Marie Skłodowska-Curie grant agreement No 777826). The first and fourth authors acknowledge partial support by MICINN/FEDER UE project, ref. PGC2018-098625-B-I00, and RED2018-102511-T. This chapter was written together with another chapter of the current handbook, called “Influence of Color Spaces for Deep Learning Image Colorization.” All authors have contributed to both chapters.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Section Editor information
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this entry
Cite this entry
Ballester, C., Carrillo, H., Clément, M., Vitoria, P. (2022). Analysis of Different Losses for Deep Learning Image Colorization. In: Chen, K., Schönlieb, CB., Tai, XC., Younces, L. (eds) Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging. Springer, Cham. https://doi.org/10.1007/978-3-030-03009-4_127-1
Download citation
DOI: https://doi.org/10.1007/978-3-030-03009-4_127-1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03009-4
Online ISBN: 978-3-030-03009-4
eBook Packages: Springer Reference MathematicsReference Module Computer Science and Engineering