BabyFlow: 3D modeling of realistic and expressive infant faces

TL;DR

BabyFlow is a novel 3D modeling framework for infant faces that disentangles identity and expression, enabling realistic synthesis, expression transfer, and improved reconstruction, which can aid early developmental disorder detection.

Contribution

It introduces BabyFlow, a probabilistic generative model using normalizing flows for flexible, independent control of infant face identity and expression, addressing data scarcity and variability.

Findings

Enhanced 3D reconstruction accuracy in expressive regions

Effective cross-age expression transfer from adults to infants

High-fidelity 2D infant image generation with consistent 3D geometry

Abstract

Early detection of developmental disorders can be aided by analyzing infant craniofacial morphology, but modeling infant faces is challenging due to limited data and frequent spontaneous expressions. We introduce BabyFlow, a generative AI model that disentangles facial identity and expression, enabling independent control over both. Using normalizing flows, BabyFlow learns flexible, probabilistic representations that capture the complex, non-linear variability of expressive infant faces without restrictive linear assumptions. To address scarce and uncontrolled expressive data, we perform cross-age expression transfer, adapting expressions from adult 3D scans to enrich infant datasets with realistic and systematic expressive variants. As a result, BabyFlow improves 3D reconstruction accuracy, particularly in highly expressive regions such as the mouth, eyes, and nose, and supports synthesis and modification of infant expressions while preserving identity. Additionally, by integrating with diffusion models, BabyFlow generates high-fidelity 2D infant images with consistent 3D geometry, providing powerful tools for data augmentation and early facial analysis.