BLANKET: Anonymizing Faces in Infant Video Recordings

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00387135" target="_blank" >RIV/68407700:21230/25:00387135 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICDL63968.2025.11204388" target="_blank" >https://doi.org/10.1109/ICDL63968.2025.11204388</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICDL63968.2025.11204388" target="_blank" >10.1109/ICDL63968.2025.11204388</a>

Jazyk výsledku

angličtina

Název v původním jazyce

BLANKET: Anonymizing Faces in Infant Video Recordings

Popis výsledku v původním jazyce

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 at https://github.com/ctu-vras/blanket-infant-face-anonym.

Název v anglickém jazyce

BLANKET: Anonymizing Faces in Infant Video Recordings

Popis výsledku anglicky

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 at https://github.com/ctu-vras/blanket-infant-face-anonym.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA25-18113S" target="_blank" >GA25-18113S: Pochopení vývoje reprezentací těla kojenců prostřednictvím humanoidních robotů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 IEEE International Conference on Development and Learning (ICDL)

ISBN

979-8-3315-4343-3

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

—

Název nakladatele

IEEE Conference Publications

Místo vydání

Piscataway

Místo konání akce

Praha

Datum konání akce

16. 9. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—