Age-Inclusive 3D Human Mesh Recovery for Action-Preserving Data Anonymization

TL;DR

This paper introduces AionHMR, a novel framework for inclusive 3D human mesh recovery across all ages, improving accuracy for children and infants while preserving privacy and enabling action analysis.

Contribution

The work presents a new optimization and deep learning approach that extends existing models to accurately reconstruct 3D meshes for children and infants, addressing a significant domain gap.

Findings

Enhanced 3D shape and pose estimation for children and infants.

Maintained high accuracy for adult human reconstruction.

Created the 3D-BabyRobot dataset for action-preserving 3D reconstructions.

Abstract

While three-dimensional (3D) shape and pose estimation is a highly researched area that has yielded significant advances, the resulting methods, despite performing well for the adult population, generally fail to generalize effectively to children and infants. This paper addresses this challenge by introducing AionHMR, a comprehensive framework designed to bridge this domain gap. We propose an optimization-based method that extends a top-performing model by incorporating the SMPL-A body model, enabling the concurrent and accurate modeling of adults, children, and infants. Leveraging this approach, we generated pseudo-ground-truth annotations for publicly available child and infant image databases. Using these new training data, we then developed and trained a specialized transformer-based deep learning model capable of real-time 3D age-inclusive human reconstruction. Extensive experiments demonstrate that our methods significantly improve shape and pose estimation for children and infants without compromising accuracy on adults. Importantly, our reconstructed meshes serve as privacy-preserving substitutes for raw images, retaining essential action, pose, and geometry information while enabling anonymized datasets release. As a demonstration, we introduce the 3D-BabyRobot dataset, a collection of action-preserving 3D reconstructions of children interacting with robots. This work bridges a crucial domain gap and establishes a foundation for inclusive, privacy-aware, and age-diverse 3D human modeling.