Research

Paper

AI LLM March 11, 2026

Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity

Authors

Zhengyao Fang, Zexi Jia, Yijia Zhong, Pengcheng Luo, Jinchao Zhang, Guangming Lu, Jun Yu, Wenjie Pei

Abstract

Recent advances in text-to-image (T2I) generation have greatly improved visual quality, yet producing images that appear visually authentic to real-world photography remains challenging. This is partly due to biases in existing evaluation paradigms: human ratings and preference-trained metrics often favor visually vivid images with exaggerated saturation and contrast, which make generations often too vivid to be real even when prompted for realistic-style images. To address this issue, we present Color Fidelity Dataset (CFD) and Color Fidelity Metric (CFM) for objective evaluation of color fidelity in realistic-style generations. CFD contains over 1.3M real and synthetic images with ordered levels of color realism, while CFM employs a multimodal encoder to learn perceptual color fidelity. In addition, we propose a training-free Color Fidelity Refinement (CFR) that adaptively modulates spatial-temporal guidance scale in generation, thereby enhancing color authenticity. Together, CFD supports CFM for assessment, whose learned attention further guides CFR to refine T2I fidelity, forming a progressive framework for assessing and improving color fidelity in realistic-style T2I generation. The dataset and code are available at https://github.com/ZhengyaoFang/CFM.

Metadata

arXiv ID: 2603.10990
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-11
Fetched: 2026-03-12 04:21

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.10990v1</id>\n    <title>Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity</title>\n    <updated>2026-03-11T17:18:12Z</updated>\n    <link href='https://arxiv.org/abs/2603.10990v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.10990v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Recent advances in text-to-image (T2I) generation have greatly improved visual quality, yet producing images that appear visually authentic to real-world photography remains challenging. This is partly due to biases in existing evaluation paradigms: human ratings and preference-trained metrics often favor visually vivid images with exaggerated saturation and contrast, which make generations often too vivid to be real even when prompted for realistic-style images. To address this issue, we present Color Fidelity Dataset (CFD) and Color Fidelity Metric (CFM) for objective evaluation of color fidelity in realistic-style generations. CFD contains over 1.3M real and synthetic images with ordered levels of color realism, while CFM employs a multimodal encoder to learn perceptual color fidelity. In addition, we propose a training-free Color Fidelity Refinement (CFR) that adaptively modulates spatial-temporal guidance scale in generation, thereby enhancing color authenticity. Together, CFD supports CFM for assessment, whose learned attention further guides CFR to refine T2I fidelity, forming a progressive framework for assessing and improving color fidelity in realistic-style T2I generation. The dataset and code are available at https://github.com/ZhengyaoFang/CFM.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-11T17:18:12Z</published>\n    <arxiv:comment>accepted by CVPR2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Zhengyao Fang</name>\n    </author>\n    <author>\n      <name>Zexi Jia</name>\n    </author>\n    <author>\n      <name>Yijia Zhong</name>\n    </author>\n    <author>\n      <name>Pengcheng Luo</name>\n    </author>\n    <author>\n      <name>Jinchao Zhang</name>\n    </author>\n    <author>\n      <name>Guangming Lu</name>\n    </author>\n    <author>\n      <name>Jun Yu</name>\n    </author>\n    <author>\n      <name>Wenjie Pei</name>\n    </author>\n  </entry>"
}