WaFusion: A Wavelet-Enhanced Diffusion Framework for Face Morph Generation

TL;DR

WaFusion introduces a wavelet-enhanced diffusion framework that generates high-quality, realistic face morphs with minimal artifacts, improving biometric security by addressing face morphing vulnerabilities.

Contribution

The paper presents WaFusion, a novel combination of wavelet decomposition and diffusion models for efficient, high-quality face morph generation, surpassing existing methods in biometric security applications.

Findings

WaFusion produces high-resolution, realistic face morphs with fewer artifacts.

The framework outperforms state-of-the-art methods on multiple biometric datasets.

WaFusion achieves superior biometric metrics such as APCER, BPCER, and EER.

Abstract

Biometric face morphing poses a critical challenge to identity verification systems, undermining their security and robustness. To address this issue, we propose WaFusion, a novel framework combining wavelet decomposition and diffusion models to generate high-quality, realistic morphed face images efficiently. WaFusion leverages the structural details captured by wavelet transforms and the generative capabilities of diffusion models, producing face morphs with minimal artifacts. Experiments conducted on FERET, FRGC, FRLL, and WVU Twin datasets demonstrate WaFusion's superiority over state-of-the-art methods, producing high-resolution morphs with fewer artifacts. Our framework excels across key biometric metrics, including the Attack Presentation Classification Error Rate (APCER), Bona Fide Presentation Classification Error Rate (BPCER), and Equal Error Rate (EER). This work sets a new benchmark in biometric morph generation, offering a cutting-edge and efficient solution to enhance biometric security systems.