Identity-Aware Hand Mesh Estimation and Personalization from RGB Images

TL;DR

This paper introduces an identity-aware approach for 3D hand mesh reconstruction from RGB images, leveraging intrinsic shape parameters for personalization and improved accuracy in AR/VR applications.

Contribution

It presents a novel identity-aware hand mesh estimation model and a personalization pipeline for unseen subjects using minimal unlabeled images.

Findings

Outperforms existing anonymous methods on public datasets.

Personalization effectively calibrates shape parameters for new users.

Identity information improves hand mesh reconstruction accuracy.

Abstract

Reconstructing 3D hand meshes from monocular RGB images has attracted increasing amount of attention due to its enormous potential applications in the field of AR/VR. Most state-of-the-art methods attempt to tackle this task in an anonymous manner. Specifically, the identity of the subject is ignored even though it is practically available in real applications where the user is unchanged in a continuous recording session. In this paper, we propose an identity-aware hand mesh estimation model, which can incorporate the identity information represented by the intrinsic shape parameters of the subject. We demonstrate the importance of the identity information by comparing the proposed identity-aware model to a baseline which treats subject anonymously. Furthermore, to handle the use case where the test subject is unseen, we propose a novel personalization pipeline to calibrate the intrinsic shape parameters using only a few unlabeled RGB images of the subject. Experiments on two large scale public datasets validate the state-of-the-art performance of our proposed method.