Analysis of Different Losses for Deep Learning Image Colorization

Coloma Ballester (), Hernan Carrillo (), Michaël Clément () and Patricia Vitoria ()
Additional contact information
Coloma Ballester: University Pompeu Fabra
Hernan Carrillo: Université de Bordeaux, LaBRI, CNRS, Bordeaux INP
Michaël Clément: Université de Bordeaux, LaBRI, CNRS, Bordeaux INP
Patricia Vitoria: University Pompeu Fabra

Chapter 21 in Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging, 2023, pp 821-846 from Springer

Abstract: 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.

Keywords: Image colorization; Deep learning; Loss functions; Color spaces (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-98661-2_127

Ordering information: This item can be ordered from
http://www.springer.com/9783030986612

DOI: 10.1007/978-3-030-98661-2_127

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().