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

TL;DR

IdentiFace is a new diffusion-based framework that improves suspect face generation in crime investigations through multi-modal inputs and iterative feature adjustment, outperforming existing methods.

Contribution

The paper introduces IdentiFace, incorporating multi-modal inputs and iterative generation to enhance identifiable suspect face creation, along with a facial identity loss and new datasets.

Findings

Achieves superior identity retrieval performance.

Effective in real-world crime investigation scenarios.

Outperforms existing face generation methods.

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.