FlowID : Enhancing Forensic Identification with Latent Flow-Matching Models

2026-03-31

AI Summary

This study addresses the challenge of identifying individuals in violent death cases where severe facial injuries render conventional recognition methods ineffective. To this end, the authors propose FlowID, an identity-preserving facial reconstruction approach that integrates latent-space flow-matching generative modeling, a single-image fine-tuning strategy, and attention-guided local editing masks. This framework enables high-quality facial reconstruction with low memory consumption and supports local deployment. The work also introduces InjuredFaces, the first benchmark dataset specifically curated for extreme facial trauma scenarios. Experimental results demonstrate that FlowID significantly outperforms existing open-source methods in both identity consistency and image fidelity.

Abstract

Every day, many people die under violent circumstances, whether from crimes, war, migration, or climate disasters. Medico-legal and law enforcement institutions document many portraits of the deceased for evidence, but cannot immediately carry out identification on them. While traditional image editing tools can process these photos for public release, the workflow is lengthy and produces suboptimal results. In this work, we leverage advances in image generation models, which can now produce photorealistic human portraits, to introduce FlowID, an identity-preserving facial reconstruction method. Our approach combines single-image fine-tuning, which adapts the generative model to out-of-distribution injured faces, with attention-based masking that localizes edits to damaged regions while preserving identity-critical features. Together, these components enable the removal of artifacts from violent death while retaining sufficient identity information to support identification. To evaluate our method, we introduce InjuredFaces, a novel benchmark for identity-preserving facial reconstruction under severe facial damage. Beyond serving as an evaluation tool for this work, InjuredFaces provides a standardized resource for the community to study and compare methods addressing facial reconstruction in extreme conditions. Experimental results show that FlowID outperforms state-of-the-art open-source methods while maintaining low memory requirements, making it suitable for local deployment without compromising data privacy.

Problem

• forensic identification
• facial reconstruction
• identity preservation
• injured faces
• violent death

Innovation

• identity-preserving facial reconstruction
• latent flow-matching
• single-image fine-tuning
• attention-based masking
• InjuredFaces benchmark