综述图像自动着色技术发展，提出美学评估新方法。
Computer-aided Colorization State-of-the-science: A Survey
- 按技术演进梳理图像着色研究，分图形、视觉到融合三阶段。
- 对7个主流模型进行美学评估，发现重建指标无法反映人眼偏好。
- 强调主观美感的重要性，适合研究图像生成与人类感知的学者。
本文综述计算机辅助着色技术的研究进展。我们认为，着色任务起源于计算机图形学，因计算机视觉的引入而蓬勃发展，并趋向视觉与图形的融合，因此提出新的分类体系，按时间顺序组织全文。我们扩展了现有的基于重建的评估方法，认为应引入美学评估以更贴近人类视觉需求和情感反应。对七个代表性无条件着色模型进行了美学评估，讨论了其与传统重建指标的差异。最后，本文指出现有未解问题，并提出未来值得探索的方向。相关项目可在 https://github.com/DanielCho-HK/Colorization 获取。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。