mlsanityData to 14 Oct 2026

Latent Diffusion Based Face Enhancement under Degraded Conditions for Forensic Face Recognition

arXiv 2508.00941 ↗First posted 31 Jul 2025cs.CVcited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 13 of its 22 references that are in the map. First posted on arXiv 31 Jul 2025.

Builds on

13 of 22 references.

References · 13

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  3. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  5. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  7. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  8. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  9. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  10. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
  11. 2022Simple Baselines for Image Restorationcited by 708
  12. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
1 more
  1. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration
  2. 2024DR-BFR: Degradation Representation with Diffusion Models for Blind Face Restoration
  3. 2023Identity-Preserving Aging of Face Images via Latent Diffusion Models
  4. 2023Controllable Inversion of Black-Box Face Recognition Models via Diffusion
  5. 2026Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
  6. 2024ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
  7. 2023DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models
  8. 2024DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis