用多模态迭代扩散生成可识别嫌疑人面孔，提升刑侦画像准确率。
IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations
- 融合多模态输入增强条件控制，避免生成歧义。
- 通过迭代调整实现关键特征优化，身份识别率显著提升。
- 专为刑侦设计，适合司法与公安系统实际应用。
嫌疑人脸生成在犯罪调查中仍面临技术挑战。传统绘图流程效率低、质量差，而基于扩散模型的方法在文本到图像生成中存在条件模糊问题，单次生成也易受采样方差影响。本文提出IdentiFace，一种新型的可识别嫌疑人面部生成扩散框架，通过（1）多模态输入设计强化条件控制，（2）迭代生成流程实现可识别特征调整。此外，我们引入面部身份损失函数，并构建两个任务专用数据集。在合成数据集和真实场景中的全面实验表明，IdentiFace在身份检索性能上优于现有方法，展现出强大的实际应用潜力。
原文摘要 · Abstract (English)
Suspect face generation remains a technical challenge in crime investigations. Traditional sketch-drawing workflows suffer from low efficiency and quality, while diffusion-based approaches still face intrinsic limitations on conditional ambiguity for text-to-image models and sampling variance for one-shot generation. We proposed IdentiFace, a novel diffusion-based framework for identifiable suspect face generation, which addressed these issues through (1) multi-modal input design to strengthen conditional control, and (2) an iterative generation pipeline enabling identifiable feature adjustment. We additionally contributed a facial identity loss and two task-specific datasets. Comprehensive experiments on synthetic datasets and in real-world scenarios indicate that IdentiFace achieves superior performance over existing methods, especially in terms of identity retrieval, and shows strong potential for practical applications.
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。