Latent Diffusion Based Face Enhancement under Degraded Conditions for Forensic Face Recognition
This work addresses the challenge of improving face recognition accuracy under forensically relevant degradations, such as compression artefacts and noise, for forensic applications, representing a strong specific gain rather than a broad paradigm shift.
The paper tackled the problem of severe performance degradation in face recognition systems when processing low-quality forensic evidence imagery by evaluating latent diffusion-based enhancement, resulting in an increase in overall recognition accuracy from 29.1% to 84.5% (a 55.4 percentage point improvement).
Face recognition systems experience severe performance degradation when processing low-quality forensic evidence imagery. This paper presents an evaluation of latent diffusion-based enhancement for improving face recognition under forensically relevant degradations. Using a dataset of 3,000 individuals from LFW with 24,000 recognition attempts, we implement the Flux.1 Kontext Dev pipeline with Facezoom LoRA adaptation to test against seven degradation categories, including compression artefacts, blur effects, and noise contamination. Our approach demonstrates substantial improvements, increasing overall recognition accuracy from 29.1% to 84.5% (55.4 percentage point improvement, 95% CI: [54.1, 56.7]). Statistical analysis reveals significant performance gains across all degradation types, with effect sizes exceeding conventional thresholds for practical significance. These findings establish the potential of sophisticated diffusion based enhancement in forensic face recognition applications.