mlsanityData to 14 Oct 2026

Temporally coherent video anonymization through GAN inpainting

arXiv 2106.02328 ↗First posted 4 Jun 2021cs.CV cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

This work tackles the problem of temporally coherent face anonymization in natural video streams.We propose JaGAN, a two-stage system starting with detecting and masking out faces with black image patches in all individual frames of the video. The second stage leverages a privacy-preserving Video Generative Adversarial Network designed to inpaint the missing image patches with artificially generated faces. Our initial experiments reveal that image based generative models are not capable of inpainting patches showing temporal coherent appearance across neighboring video frames. To address this issue we introduce a newly curated video collection, which is made publicly available for the research community along with this paper. We also introduce the Identity Invariance Score IdI as a means to quantify temporal coherency between neighboring frames.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

26 of 41 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  6. 2014Conditional Generative Adversarial Netscited by 2,162
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  8. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  9. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  10. 2016Least Squares Generative Adversarial Networkscited by 1,001
  11. 2016Generative Adversarial Text to Image Synthesiscited by 735
  12. 2018Which Training Methods for GANs do actually Converge?cited by 679
14 more
  1. 2017Wasserstein GANcited by 639
  2. 2018Generative Image Inpainting with Contextual Attentioncited by 580
  3. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  4. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  5. 2018Video-to-Video Synthesiscited by 390
  6. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  7. 2017Deep Photo Style Transfercited by 168
  8. 2016Semantic Image Inpainting with Deep Generative Modelscited by 157
  9. 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
  10. 2020CIAGAN: Conditional Identity Anonymization Generative Adversarial Networkscited by 88
  11. 2017Generative Face Completioncited by 79
  12. 2016Finding Tiny Facescited by 72
  13. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  14. 2016Defeating Image Obfuscation with Deep Learningcited by 43

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 4; 2025: 1.

7 papers.

  1. 2022Realistic Full-Body Anonymization with Surface-Guided GANscited by 15
  2. 2023EgoBlur: Responsible Innovation in Ariacited by 12
  3. 2024Face De-identification: State-of-the-art Methods and Comparative Studiescited by 9
  4. 2024RID-TWIN: An end-to-end pipeline for automatic face de-identification in videoscited by 2
  5. 2024Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservationcited by 2
  6. 2024My Body My Choice: Human-Centric Full-Body Anonymizationcited by 2
  7. 2025BLANKET: Anonymizing Faces in Infant Video Recordingscited by 2