BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs

TL;DR

BabyNet is a novel system that reconstructs 3D baby faces from uncalibrated photos by learning a baby-specific facial shape space and mapping 2D images to 3D geometry, outperforming existing methods.

Contribution

Introduces BabyNet, the first baby-specific 3D face reconstruction system using deep learning and transfer learning techniques.

Findings

BabyNet outperforms classical model-fitting methods.

Adult-based models cannot accurately reconstruct baby faces.

BabyNet effectively models baby-specific facial geometry.

Abstract

We present a 3D face reconstruction system that aims at recovering the 3D facial geometry of babies from uncalibrated photographs, BabyNet. Since the 3D facial geometry of babies differs substantially from that of adults, baby-specific facial reconstruction systems are needed. BabyNet consists of two stages: 1) a 3D graph convolutional autoencoder learns a latent space of the baby 3D facial shape; and 2) a 2D encoder that maps photographs to the 3D latent space based on representative features extracted using transfer learning. In this way, using the pre-trained 3D decoder, we can recover a 3D face from 2D images. We evaluate BabyNet and show that 1) methods based on adult datasets cannot model the 3D facial geometry of babies, which proves the need for a baby-specific method, and 2) BabyNet outperforms classical model-fitting methods even when a baby-specific 3D morphable model, such as BabyFM, is used.