MCIQA-2K：用于彩色化图像的多维数据集与无参考质量评估基准
MCIQA-2K: A Multi-Dimensional Dataset and No-Reference Quality Assessment Benchmark for Colorized Images
浏览论文内容
中文总结 AI 辅助
针对图像彩色化任务中全参考质量评估失效的问题，提出MCIQA-2K多维基准数据集及多分支无参考质量评估框架MCIQA，实验证明其性能优于现有方法。
中文摘要 AI 辅助
图像彩色化是一个本质上不适定的任务，因为单个灰度图像可能对应多个合理的彩色化结果。因此，传统的全参考图像质量评估（IQA）指标无法准确反映人类对彩色化图像的感知偏好。在本文中，我们提出了MCIQA-2K，一个专门用于彩色化图像无参考质量评估的大规模多维基准。我们构建了一个包含由五种代表性彩色化模型生成的2,000张彩色化图像的数据集，并提供了跨三个感知维度的人工标注：颜色拖尾、语义颜色错位和全局自然度。基于所提出的基准，我们进一步引入了MCIQA，一个专门用于彩色化图像的多分支无参考图像质量评估（NR-IQA）框架。大量实验表明，MCIQA在所提出的基准上显著优于现有的全参考和无参考IQA方法，同时在多个广泛使用的IQA数据集上也展现出具有竞争力的泛化能力。数据集和代码可在该https URL公开获取。
英文摘要
Image colorization is an inherently ill-posed task, since a single grayscale image may correspond to multiple plausible colorized results. Consequently, conventional full-reference image quality assessment (IQA) metrics fail to accurately reflect human perceptual preferences for colorized images. In this paper, we present MCIQA-2K, a large-scale multi-dimensional benchmark specifically designed for no-reference quality assessment of colorized images. We construct a dataset containing 2,000 colorized images generated by five representative colorization models, together with human annotations across three perceptual dimensions: color smearing, semantic color misalignment, and global naturalness. Building upon the proposed benchmark, we further introduce MCIQA, a dedicated multi-branch NR-IQA framework for colorized images. Extensive experiments demonstrate that MCIQA significantly outperforms existing full-reference and no-reference IQA methods on the proposed benchmark, while also exhibiting competitive generalization capability on several widely-used IQA datasets. The dataset and code are publicly available at https://github.com/ARBEZ-ZEBRA/MCIQA.
发表机构
- ShanghaiTech University（上海科技大学）
- Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
