# BLANKET: Anonymizing Faces in Infant Video Recordings

arXiv: https://arxiv.org/abs/2512.15542 · HTML: https://mlsanity.com/paper/2512.15542/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [DeepPrivacy: A Generative Adversarial Network for Face Anonymization](https://mlsanity.com/paper/1909.04538/) (2019)
- [CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks](https://mlsanity.com/paper/2005.09544/) (2020)
- [DiffFace: Diffusion-based Face Swapping with Facial Guidance](https://mlsanity.com/paper/2212.13344/) (2022)
- [AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding](https://mlsanity.com/paper/1711.06475/) (2017)
- [Natural and Effective Obfuscation by Head Inpainting](https://mlsanity.com/paper/1711.09001/) (2017)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [Perceptual Artifacts Localization for Image Synthesis Tasks](https://mlsanity.com/paper/2310.05590/) (2023)
- [FSNet: An Identity-Aware Generative Model for Image-based Face Swapping](https://mlsanity.com/paper/1811.12666/) (2018)
- [Shape Preserving Facial Landmarks with Graph Attention Networks](https://mlsanity.com/paper/2210.07233/) (2022)
- [Privacy-Protective-GAN for Face De-identification](https://mlsanity.com/paper/1806.08906/) (2018)
- [FIVA: Facial Image and Video Anonymization and Anonymization Defense](https://mlsanity.com/paper/2309.04228/) (2023)
- [Temporally coherent video anonymization through GAN inpainting](https://mlsanity.com/paper/2106.02328/) (2021)

## Built on by (most cited first, 2 of 2)

- [Unsafe2Safe: Controllable Image Anonymization for Downstream Utility](https://mlsanity.com/paper/2603.28605/) (2026)
- [BBoxMaskPose v2: Expanding Mutual Conditioning to 3D](https://mlsanity.com/paper/2601.15200/) (2026)

## Abstract (arXiv)

Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANonymization with Keypoint dEtection consisTency), a novel approach designed to anonymize infant faces in video recordings while preserving essential facial attributes. Our method comprises two stages. First, a new random face, compatible with the original identity, is generated via inpainting using a diffusion model. Second, the new identity is seamlessly incorporated into each video frame through temporally consistent face swapping with authentic expression transfer. The method is evaluated on a dataset of short video recordings of babies and is compared to the popular anonymization method, DeepPrivacy2. Key metrics assessed include the level of de-identification, preservation of facial attributes, impact on human pose estimation (as an example of a downstream task), and presence of artifacts. Both methods alter the identity, and our method outperforms DeepPrivacy2 in all other respects. The code is available as an easy-to-use anonymization demo at https://github.com/ctu-vras/blanket-infant-face-anonym.