Benchmarking 2D Egocentric Hand Pose Datasets

TL;DR

This paper analyzes existing egocentric hand pose datasets, proposing a new evaluation protocol, and identifies the most promising datasets for 2D hand pose estimation despite the lack of an ideal benchmark.

Contribution

It introduces a novel dataset evaluation protocol and provides a comprehensive analysis of current datasets for 2D egocentric hand pose estimation.

Findings

H2O and GANerated Hands are the most promising datasets

Most datasets are tailored for specific use cases

No single ideal benchmark dataset exists

Abstract

Hand pose estimation from egocentric video has broad implications across various domains, including human-computer interaction, assistive technologies, activity recognition, and robotics, making it a topic of significant research interest. The efficacy of modern machine learning models depends on the quality of data used for their training. Thus, this work is devoted to the analysis of state-of-the-art egocentric datasets suitable for 2D hand pose estimation. We propose a novel protocol for dataset evaluation, which encompasses not only the analysis of stated dataset characteristics and assessment of data quality, but also the identification of dataset shortcomings through the evaluation of state-of-the-art hand pose estimation models. Our study reveals that despite the availability of numerous egocentric databases intended for 2D hand pose estimation, the majority are tailored for specific use cases. There is no ideal benchmark dataset yet; however, H2O and GANerated Hands datasets emerge as the most promising real and synthetic datasets, respectively.