cs.AI updates on arXiv.org 07月28日 12:42
Gen-AI Police Sketches with Stable Diffusion
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文研究多模态AI在自动化和提升嫌疑人画像中的应用,通过三种模型评估,证实了优化自注意力和交叉注意力层能显著提高画像与描述的匹配度,其中模型1在结构相似度和信噪比上表现最佳。

arXiv:2507.18667v1 Announce Type: cross Abstract: This project investigates the use of multimodal AI-driven approaches to automate and enhance suspect sketching. Three pipelines were developed and evaluated: (1) baseline image-to-image Stable Diffusion model, (2) same model integrated with a pre-trained CLIP model for text-image alignment, and (3) novel approach incorporating LoRA fine-tuning of the CLIP model, applied to self-attention and cross-attention layers, and integrated with Stable Diffusion. An ablation study confirmed that fine-tuning both self- and cross-attention layers yielded the best alignment between text descriptions and sketches. Performance testing revealed that Model 1 achieved the highest structural similarity (SSIM) of 0.72 and a peak signal-to-noise ratio (PSNR) of 25 dB, outperforming Model 2 and Model 3. Iterative refinement enhanced perceptual similarity (LPIPS), with Model 3 showing improvement over Model 2 but still trailing Model 1. Qualitatively, sketches generated by Model 1 demonstrated the clearest facial features, highlighting its robustness as a baseline despite its simplicity.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

多模态AI 嫌疑人画像 模型评估
相关文章