IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations

2026-05-01

AI Summary

This work addresses the inefficiency and poor quality of suspect face generation in criminal investigations, as well as limitations of existing diffusion models in handling textual condition ambiguity and high variance in single-step sampling. To overcome these challenges, the authors propose a multimodal iterative diffusion generation framework that integrates textual descriptions and hand-drawn sketches to strengthen conditional control. The framework features an iterative refinement process with tunable identity characteristics and incorporates an identity-aware loss function. Additionally, two task-specific datasets are constructed to support evaluation. Experimental results demonstrate that the proposed method significantly outperforms current state-of-the-art approaches in both synthetic and real-world scenarios, achieving notably higher accuracy in identity retrieval and showing strong potential for practical deployment.

Abstract

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.

Problem

• suspect face generation
• identifiable face
• crime investigation
• conditional ambiguity
• sampling variance

Innovation

• multi-modal diffusion
• iterative generation
• identifiable face synthesis
• facial identity loss
• suspect face generation