Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey

TL;DR

This survey reviews methods for efficient annotation and learning in 3D hand pose estimation, highlighting challenges, existing approaches, and future directions to improve model performance with limited annotated data.

Contribution

It systematically analyzes current annotation techniques and learning strategies, providing a comprehensive overview of advancements and challenges in 3D hand pose estimation.

Findings

Manual annotation is labor-intensive and challenging.

Synthetic data and computational methods can supplement scarce annotations.

Self-supervised and domain adaptation techniques improve learning with limited data.

Abstract

In this survey, we present a systematic review of 3D hand pose estimation from the perspective of efficient annotation and learning. 3D hand pose estimation has been an important research area owing to its potential to enable various applications, such as video understanding, AR/VR, and robotics. However, the performance of models is tied to the quality and quantity of annotated 3D hand poses. Under the status quo, acquiring such annotated 3D hand poses is challenging, e.g., due to the difficulty of 3D annotation and the presence of occlusion. To reveal this problem, we review the pros and cons of existing annotation methods classified as manual, synthetic-model-based, hand-sensor-based, and computational approaches. Additionally, we examine methods for learning 3D hand poses when annotated data are scarce, including self-supervised pretraining, semi-supervised learning, and domain adaptation. Based on the study of efficient annotation and learning, we further discuss limitations and possible future directions in this field.