mlsanityData to 7 Oct 2026

IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models

arXiv 2308.04995 ↗First posted 9 Aug 2023cs.CVcited by 72

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

The availability of large-scale authentic face databases has been crucial to the significant advances made in face recognition research over the past decade. However, legal and ethical concerns led to the recent retraction of many of these databases by their creators, raising questions about the continuity of future face recognition research without one of its key resources. Synthetic datasets have emerged as a promising alternative to privacy-sensitive authentic data for face recognition development. However, recent synthetic datasets that are used to train face recognition models suffer either from limitations in intra-class diversity or cross-class (identity) discrimination, leading to less optimal accuracies, far away from the accuracies achieved by models trained on authentic data. This paper targets this issue by proposing IDiff-Face, a novel approach based on conditional latent diffusion models for synthetic identity generation with realistic identity variations for face recognition training. Through extensive evaluations, our proposed synthetic-based face recognition approach pushed the limits of state-of-the-art performances, achieving, for example, 98.00% accuracy on the Labeled Faces in the Wild (LFW) benchmark, far ahead from the recent synthetic-based face recognition solutions with 95.40% and bridging the gap to authentic-based face recognition with 99.82% accuracy.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 45 of its 63 references that are in the map. First posted on arXiv 9 Aug 2023.

Builds on

45 of 63 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  10. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  11. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
31 more
  1. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  2. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  3. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  4. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  5. 2014Learning Face Representation from Scratchcited by 451
  6. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
  7. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 267
  8. 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 258
  9. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 219
  10. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  11. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
  12. 2021SynFace: Face Recognition with Synthetic Datacited by 106
  13. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  14. 2021GAN-Control: Explicitly Controllable GANscited by 91
  15. 2022SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Datacited by 63
  16. 2020CONFIG: Controllable Neural Face Image Generationcited by 61
  17. 2020GIF: Generative Interpretable Facescited by 53
  18. 2022Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectorscited by 47
  19. 2016UMDFaces: An Annotated Face Dataset for Training Deep Networkscited by 42
  20. 2023Synthetic Data for Face Recognition: Current State and Future Prospectscited by 38
  21. 2021PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillationcited by 36
  22. 2022Unsupervised Face Recognition using Unlabeled Synthetic Datacited by 27
  23. 2023Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognitioncited by 27
  24. 2023DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Modelscited by 22
  25. 2023ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generationcited by 22
  26. 2017Semantically Decomposing the Latent Spaces of Generative Adversarial Networkscited by 19
  27. 2022QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantizationcited by 18
  28. 2023SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Datacited by 17
  29. 2018FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesiscited by 14
  30. 2017Representation Learning by Rotating Your Facescited by 7
  31. 2020An Assessment of GANs for Identity-related Applicationscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 36; 2025: 19; 2026: 14.

72 papers.

Sort:

By area:

  1. 2024SDFR: Synthetic Data for Face Recognition Competitioncited by 28
  2. 2024Privacy-Preserving Face Recognition Using Trainable Feature Subtractioncited by 24
  3. 2024FRoundation: Are Foundation Models Ready for Face Recognition?cited by 22
  4. 2023FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Datacited by 21
  5. 2024ID3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognitioncited by 18
  6. 2024Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectorscited by 15
  7. 2024Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Datacited by 13
  8. 202550 Years of Automated Face Recognitioncited by 13
  9. 2024Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusioncited by 12
  10. 2024Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Modelcited by 12
  11. 2024HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hyperspherecited by 12
  12. 2025Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusioncited by 12
38 more
  1. 2023Bias and Diversity in Synthetic-based Face Recognitioncited by 11
  2. 2024ONOT: a High-Quality ICAO-compliant Synthetic Mugshot Datasetcited by 10
  3. 2024CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognitioncited by 10
  4. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  5. 2024Digi2Real: Bridging the Realism Gap in Synthetic Data Face Recognition via Foundation Modelscited by 9
  6. 2024SlerpFace: Face Template Protection via Spherical Linear Interpolationcited by 8
  7. 2024VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognitioncited by 8
  8. 2024Rethinking Impersonation and Dodging Attacks on Face Recognition Systemscited by 7
  9. 2024AdaDistill: Adaptive Knowledge Distillation for Deep Face Recognitioncited by 7
  10. 2024SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributescited by 6
  11. 2024SynFER: Towards Boosting Facial Expression Recognition with Synthetic Datacited by 6
  12. 2025ID-Booth: Identity-consistent Face Generation with Diffusion Modelscited by 6
  13. 2024Diffusion-based Data Augmentation for Object Counting Problemscited by 5
  14. 2024VIGFace: Virtual Identity Generation for Privacy-Free Face Recognitioncited by 5
  15. 2024Synthetic to Authentic: Transferring Realism to 3D Face Renderings for Boosting Face Recognitioncited by 5
  16. 2025Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generationcited by 5
  17. 2024If It's Not Enough, Make It So: Reducing Authentic Data Demand in Face Recognition through Synthetic Facescited by 4
  18. 2024Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Modelscited by 4
  19. 2024A Survey on Drowsiness Detection -- Modern Applications and Methodscited by 4
  20. 2023EyePreserve: Identity-Preserving Iris Synthesiscited by 3
  21. 2024Goldilocks Test Sets for Face Verificationcited by 3
  22. 2024The Impact of Balancing Real and Synthetic Data on Accuracy and Fairness in Face Recognitioncited by 3
  23. 2024Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identitiescited by 3
  24. 2024Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentationcited by 3
  25. 2025UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognitioncited by 3
  26. 2025AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognitioncited by 3
  27. 2025Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Modelscited by 3
  28. 2025NegFaceDiff: The Power of Negative Context in Identity-Conditioned Diffusion for Synthetic Face Generationcited by 3
  29. 2024Massively Annotated Datasets for Assessment of Synthetic and Real Data in Face Recognitioncited by 2
  30. 2024Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verificationcited by 2
  31. 2024StyleDiT: A Unified Framework for Diverse Child and Partner Faces Synthesis with Style Latent Diffusion Transformercited by 2
  32. 2025FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Imagescited by 2
  33. 2025Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Datacited by 2
  34. 2026IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbationcited by 2
  35. 2024Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimizationcited by 1
  36. 2024Analyzing the Feature Extractor Networks for Face Image Synthesiscited by 1
  37. 2024How Knowledge Distillation Mitigates the Synthetic Gap in Fair Face Recognitioncited by 1
  38. 2025ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesiscited by 1

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Controllable Inversion of Black-Box Face Recognition Models via Diffusion
  2. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Model
  3. 2026Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models
  4. 2023GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations
  5. 2024Identity-Focused Inference and Extraction Attacks on Diffusion Models
  6. 2024Detection of Synthetic Face Images: Accuracy, Robustness, Generalization
  7. 2026On Applicability of Synthetic Datasets for Facial Expression Recognition
  8. 2025Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization