Computer-aided Colorization State-of-the-science: A Survey

TL;DR

This survey reviews the evolution of computer-aided colorization, emphasizing the integration of computer vision and graphics, and introduces aesthetic assessment techniques to evaluate colorization quality more aligned with human perception.

Contribution

It provides a comprehensive taxonomy, extends evaluation methods with aesthetic assessment, and discusses future research directions in computer-aided colorization.

Findings

Aesthetic assessment offers better alignment with human perception.

Extended evaluation techniques improve colorization quality measurement.

Identified unresolved issues and future research areas.

Abstract

This paper reviews published research in the field of computer-aided colorization technology. We argue that the colorization task originates from computer graphics, prospers by introducing computer vision, and tends to the fusion of vision and graphics, so we put forward our taxonomy and organize the whole paper chronologically. We extend the existing reconstruction-based colorization evaluation techniques, considering that aesthetic assessment of colored images should be introduced to ensure that colorization satisfies human visual-related requirements and emotions more closely. We perform the colorization aesthetic assessment on seven representative unconditional colorization models and discuss the difference between our assessment and the existing reconstruction-based metrics. Finally, this paper identifies unresolved issues and proposes fruitful areas for future research and development. Access to the project associated with this survey can be obtained at https://github.com/DanielCho-HK/Colorization.