宇航计测技术 ›› 2025, Vol. 45 ›› Issue (1): 53-60.doi: 10.12060/j.issn.1000-7202.2025.01.10

• 精密测试技术 • 上一篇    下一篇

基于多层次特征的跨域图像生成评估方法

白文哲，李春宇*   

  1. 中国人民公安大学侦查学院，北京 100038
  • 出版日期:2025-03-15 发布日期:2025-03-27
  • 作者简介:白文哲（1996-），男，硕士，主要研究方向：电子数据检验。
  • 基金资助:
    中国人民公安大学刑事科学技术双一流创新研究专项（2023SYL06）资助。

A Cross-Domain Image Generation Evaluation Method Based on Multi-Level Features

BAI Wenzhe，LI Chunyu*   

  1. School of Criminal Investigation,People’s Public Security University of China,Beijing 100038,China
  • Online:2025-03-15 Published:2025-03-27

PDF (PC)

摘要： 针对弗雷歇初始距离（Fréchet Inception Distance，FID）指标在跨域图像生成评估时约束力低的问题，提出了一种基于多层次特征对齐距离（Multi-Level Feature Alignment Distance,MLFAD）的域差计算方法。通过引入多层次特征提取与特征对齐机制，实现生成图像与真实图像在不同层次特征尺度分布差异的全面度量，更加精确地反映图像的细节和全局信息，大幅度增强了对生成图像的约束力。试验结果表明，MLFAD的表现显著优于FID，在图像翻译、风格迁移、图像修复和图像增强等跨域图像生成任务中，域差计算值分别降低了31.7%、26.8%、41.1%和34.6%。因此，MLFAD在跨域图像生成任务的评估中具有良好的准确性和稳定性，显著提升了生成图像的清晰度、细节还原度及色彩精准度。

关键词: 图像处理, 图像质量评估, 特征提取, 特征融合

Abstract: To address the issue of low binding force of the Fréchet Inception Distance (FID) metric in cross-domain image generation evaluation,a domain difference calculation method based on the Multi-Level Feature Alignment Distance (MLFAD) is proposed.By introducing a multi-level feature extraction and feature alignment mechanism,a comprehensive measurement of the distribution differences of generated images and real images at different hierarchical feature scales is achieved,which more accurately reflects the detailed and global information of the images and significantly enhances the binding force on the generated images.The experimental results show that the performance of MLFAD is significantly better than that of the FID.In cross-domain image generation tasks such as image translation,style transfer,image restoration,and image enhancement,the domain difference has been reduced by 31.7%,26.8%,41.1%,and 34.6%,respectively.Therefore,MLFAD which has excellent accuracy and stability in the evaluation of cross-domain image generation tasks,significantly improves the clarity,detail restoration,and color accuracy of the generated images.

Key words: Image processing, Image quality assessment, Feature extraction, Feature fusion

中图分类号: 

京ICP备09048426号-4　 京公网安备 11010602060144号　版权所有 © 《宇航计测技术》编辑部