# Live Face De-Identification in Video

arXiv: https://arxiv.org/abs/1911.08348 · HTML: https://mlsanity.com/paper/1911.08348/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2019.

## Built on by (most cited first, 30 of 48)

- [Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors](https://mlsanity.com/paper/2203.13131/) (2022)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [Data Poisoning Won't Save You From Facial Recognition](https://mlsanity.com/paper/2106.14851/) (2021)
- [PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition](https://mlsanity.com/paper/2108.03764/) (2021)
- [Diff-Privacy: Diffusion-based Face Privacy Protection](https://mlsanity.com/paper/2309.05330/) (2023)
- [IdentityDP: Differential Private Identification Protection for Face Images](https://mlsanity.com/paper/2103.01745/) (2021)
- [MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation](https://mlsanity.com/paper/2111.01048/) (2021)
- [OPOM: Customized Invisible Cloak towards Face Privacy Protection](https://mlsanity.com/paper/2205.11981/) (2022)
- [RiDDLE: Reversible and Diversified De-identification with Latent Encryptor](https://mlsanity.com/paper/2303.05171/) (2023)
- [Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics](https://mlsanity.com/paper/2104.01753/) (2021)
- [G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors](https://mlsanity.com/paper/2408.09458/) (2024)
- [Realistic Full-Body Anonymization with Surface-Guided GANs](https://mlsanity.com/paper/2201.02193/) (2022)
- [My Face My Choice: Privacy Enhancing Deepfakes for Social Media Anonymization](https://mlsanity.com/paper/2211.01361/) (2022)
- [CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation](https://mlsanity.com/paper/2105.11137/) (2021)
- [Does Image Anonymization Impact Computer Vision Training?](https://mlsanity.com/paper/2306.05135/) (2023)
- [FIVA: Facial Image and Video Anonymization and Anonymization Defense](https://mlsanity.com/paper/2309.04228/) (2023)
- [StyleID: Identity Disentanglement for Anonymizing Faces](https://mlsanity.com/paper/2212.13791/) (2022)
- [Graph-based Generative Face Anonymisation with Pose Preservation](https://mlsanity.com/paper/2112.05496/) (2021)
- [Face De-identification: State-of-the-art Methods and Comparative Studies](https://mlsanity.com/paper/2411.09863/) (2024)
- [FICGAN: Facial Identity Controllable GAN for De-identification](https://mlsanity.com/paper/2110.00740/) (2021)
- [A Review on Visual Privacy Preservation Techniques for Active and Assisted Living](https://mlsanity.com/paper/2112.09422/) (2021)
- [Learnable Privacy-Preserving Anonymization for Pedestrian Images](https://mlsanity.com/paper/2207.11677/) (2022)
- [Evaluation of Human Visual Privacy Protection: A Three-Dimensional Framework and Benchmark Dataset](https://mlsanity.com/paper/2507.13981/) (2025)
- [Causal Representation Learning for Context-Aware Face Transfer](https://mlsanity.com/paper/2110.01571/) (2021)
- [Practical Digital Disguises: Leveraging Face Swaps to Protect Patient Privacy](https://mlsanity.com/paper/2204.03559/) (2022)
- [StyleGAN as a Utility-Preserving Face De-identification Method](https://mlsanity.com/paper/2212.02611/) (2022)
- [RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos](https://mlsanity.com/paper/2403.10058/) (2024)
- [Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservation](https://mlsanity.com/paper/2405.19173/) (2024)
- [Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach](https://mlsanity.com/paper/2409.02715/) (2024)
- [Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms](https://mlsanity.com/paper/2402.03188/) (2024)

## Abstract (arXiv)

We propose a method for face de-identification that enables fully automatic video modification at high frame rates. The goal is to maximally decorrelate the identity, while having the perception (pose, illumination and expression) fixed. We achieve this by a novel feed-forward encoder-decoder network architecture that is conditioned on the high-level representation of a person's facial image. The network is global, in the sense that it does not need to be retrained for a given video or for a given identity, and it creates natural looking image sequences with little distortion in time.