Multi-View Video-Based 3D Hand Pose Estimation

TL;DR

This paper introduces MuViHand, a large multi-view video dataset with ground-truth 3D hand poses, and MuViHandNet, a neural network pipeline that leverages multi-view and temporal data for improved 3D hand pose estimation.

Contribution

The paper presents a new multi-view video dataset with synthetic data and complex scenarios, along with a novel neural network architecture that effectively utilizes multi-view and temporal information for 3D hand pose estimation.

Findings

MuViHand dataset contains over 402,000 synthetic images from 6 angles.

MuViHandNet outperforms baseline methods on the new dataset.

Temporal and multi-view information significantly improve estimation accuracy.

Abstract

Hand pose estimation (HPE) can be used for a variety of human-computer interaction applications such as gesture-based control for physical or virtual/augmented reality devices. Recent works have shown that videos or multi-view images carry rich information regarding the hand, allowing for the development of more robust HPE systems. In this paper, we present the Multi-View Video-Based 3D Hand (MuViHand) dataset, consisting of multi-view videos of the hand along with ground-truth 3D pose labels. Our dataset includes more than 402,000 synthetic hand images available in 4,560 videos. The videos have been simultaneously captured from six different angles with complex backgrounds and random levels of dynamic lighting. The data has been captured from 10 distinct animated subjects using 12 cameras in a semi-circle topology where six tracking cameras only focus on the hand and the other six fixed cameras capture the entire body. Next, we implement MuViHandNet, a neural pipeline consisting of image encoders for obtaining visual embeddings of the hand, recurrent learners to learn both temporal and angular sequential information, and graph networks with U-Net architectures to estimate the final 3D pose information. We perform extensive experiments and show the challenging nature of this new dataset as well as the effectiveness of our proposed method. Ablation studies show the added value of each component in MuViHandNet, as well as the benefit of having temporal and sequential information in the dataset.