mlsanityData to 7 Oct 2026

DeepPrivacy2: Towards Realistic Full-Body Anonymization

arXiv 2211.09454 ↗First posted 17 Nov 2022cs.CVcited by 51

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures. However, current state-of-the-art limit anonymization to the task of face anonymization. In this paper, we propose a novel anonymization framework (DeepPrivacy2) for realistic anonymization of human figures and faces. We introduce a new large and diverse dataset for human figure synthesis, which significantly improves image quality and diversity of generated images. Furthermore, we propose a style-based GAN that produces high quality, diverse and editable anonymizations. We demonstrate that our full-body anonymization framework provides stronger privacy guarantees than previously proposed methods.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

36 of 53 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2017Mask R-CNNcited by 7,259
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2017NIMA: Neural Image Assessmentcited by 387
24 more
  1. 2018Everybody Dance Nowcited by 313
  2. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  3. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  4. 2017VITON: An Image-based Virtual Try-on Networkcited by 285
  5. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  6. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  7. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  8. 2018DSFD: Dual Shot Face Detectorcited by 115
  9. 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
  10. 2019Dense Intrinsic Appearance Flow for Human Pose Transfercited by 104
  11. 2017Disentangled Person Image Generationcited by 98
  12. 2018Synthesizing Images of Humans in Unseen Posescited by 96
  13. 2018Dense Pose Transfercited by 83
  14. 2020Continuous Surface Embeddingscited by 79
  15. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  16. 2017Natural and Effective Obfuscation by Head Inpaintingcited by 60
  17. 2021Neural Re-Rendering of Humans from a Single Imagecited by 59
  18. 2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53
  19. 2019Live Face De-Identification in Videocited by 48
  20. 2018A Hybrid Model for Identity Obfuscation by Face Replacementcited by 43
  21. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  22. 2022Self-Distilled StyleGAN: Towards Generation from Internet Photoscited by 37
  23. 2019EPIC: An Energy-Efficient, High-Performance GPGPU Computing Research Infrastructurecited by 22
  24. 2022Realistic Full-Body Anonymization with Surface-Guided GANscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 9; 2025: 18; 2026: 14.

51 papers.

Sort:

By area:

  1. 2023Diff-Privacy: Diffusion-based Face Privacy Protectioncited by 25
  2. 2023LDFA: Latent Diffusion Face Anonymization for Self-driving Applicationscited by 21
  3. 2024Face Anonymization Made Simplecited by 18
  4. 2023Does Image Anonymization Impact Computer Vision Training?cited by 12
  5. 2023FIVA: Facial Image and Video Anonymization and Anonymization Defensecited by 12
  6. 2025Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Drivingcited by 10
  7. 2023GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressionscited by 9
  8. 2024Latent Diffusion Models for Attribute-Preserving Image Anonymizationcited by 7
  9. 2023Anonymizing medical case-based explanations through disentanglementcited by 5
  10. 2025NullFace: Training-Free Localized Face Anonymizationcited by 4
  11. 2024Context-Aware Full Body Anonymization using Text-to-Image Diffusion Modelscited by 3
  12. 2025Video-DPRP: A Differentially Private Approach for Visual Privacy-Preserving Video Human Activity Recognitioncited by 3
38 more
  1. 2025Evaluation of Vision-LLMs in Surveillance Videocited by 3
  2. 2023Synthesizing Anyone, Anywhere, in Any Posecited by 2
  3. 2024Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservationcited by 2
  4. 2024My Body My Choice: Human-Centric Full-Body Anonymizationcited by 2
  5. 2024Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approachcited by 2
  6. 2024Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognitioncited by 2
  7. 2025The ATLAS of Traffic Lights: A Reliable Perception Framework for Autonomous Drivingcited by 2
  8. 2025LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image Generationcited by 2
  9. 2025BLANKET: Anonymizing Faces in Infant Video Recordingscited by 2
  10. 2026Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videoscited by 2
  11. 2024FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentificationcited by 1
  12. 2025SVIA: A Street View Image Anonymization Framework for Self-Driving Applicationscited by 1
  13. 2025Enabling Privacy-Aware AI-Based Ergonomic Analysiscited by 1
  14. 2025Reverse Personalizationcited by 1
  15. 2026FDeID-Toolbox: Face De-Identification Toolboxcited by 1
  16. 2026Towards Context-Aware Image Anonymization with Multi-Agent Reasoningcited by 1
  17. 2026Unsafe2Safe: Controllable Image Anonymization for Downstream Utilitycited by 1
  18. 2026GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent Optimizationcited by 1
  19. 2023PrivacyGAN: robust generative image privacycited by 0
  20. 2023Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identificationcited by 0
  21. 2023VerA: Versatile Anonymization Applicable to Clinical Facial Photographscited by 0
  22. 2024Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy Versus Performancecited by 0
  23. 2025FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methodscited by 0
  24. 2025Differentially Private 2D Human Pose Estimationcited by 0
  25. 2025Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Taskscited by 0
  26. 2025Assessing the Use of Face Swapping Methods as Face Anonymizers in Videoscited by 0
  27. 2025Facial Attribute Based Text Guided Face Anonymizationcited by 0
  28. 2025Unmasking Performance Gaps: A Comparative Study of Human Anonymization and Its Effects on Video Anomaly Detectioncited by 0
  29. 2025FLUID: Training-Free Face De-identification via Latent Identity Substitutioncited by 0
  30. 2025Privacy-Preserving Computer Vision for Industry: Three Case Studies in Human-Centric Manufacturingcited by 0
  31. 2026Evaluating the Impact of Data Anonymization on Image Retrievalcited by 0
  32. 2026Face anonymization preserving facial expressions and photometric realismcited by 0
  33. 2026Protecting and Preserving Protest Dynamics for Responsible Analysiscited by 0
  34. 2026ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymizationcited by 0
  35. 2026Swapping Faces, Saving Features: A Dual-Purpose Pipeline for Pedestrian Privacy in ITScited by 0
  36. 2026Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detectioncited by 0
  37. 2026MIRAGE: Full-Body Bystander Privacy for Smart Glasses with Consent-Based Restorationcited by 0
  38. 2026HYDRO: Towards Non-Reversible Face De-Identification Using a High-Fidelity Hybrid Diffusion and Target-Oriented Approachcited by 0

50 most cited of 51 All 51 (JSON)