InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image

by   Gyeongsik Moon, et al.

Analysis of hand-hand interactions is a crucial step towards better understanding human behavior. However, most researches in 3D hand pose estimation have focused on the isolated single hand case. Therefore, we firstly propose (1) a large-scale dataset, InterHand2.6M, and (2) a baseline network, InterNet, for 3D interacting hand pose estimation from a single RGB image. The proposed InterHand2.6M consists of 2.6M labeled single and interacting hand frames under various poses from multiple subjects. Our InterNet simultaneously performs 3D single and interacting hand pose estimation. In our experiments, we demonstrate big gains in 3D interacting hand pose estimation accuracy when leveraging the interacting hand data in InterHand2.6M. We also report the accuracy of InterNet on InterHand2.6M, which serves as a strong baseline for this new dataset. Finally, we show 3D interacting hand pose estimation results from general images. Our code and dataset are available at



page 19

page 20

page 21

page 22

page 26


Learning to Estimate 3D Hand Pose from Single RGB Images

Low-cost consumer depth cameras and deep learning have enabled reasonabl...

Parallel mesh reconstruction streams for pose estimation of interacting hands

We present a new multi-stream 3D mesh reconstruction network (MSMR-Net) ...

Depth-based hand pose estimation: methods, data, and challenges

Hand pose estimation has matured rapidly in recent years. The introducti...

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation

In natural conversation and interaction, our hands often overlap or are ...

Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements

3D interacting hand reconstruction is essential to facilitate human-mach...

Active Learning for Bayesian 3D Hand Pose Estimation

We propose a Bayesian approximation to a deep learning architecture for ...

ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

Estimating the articulated 3D hand-object pose from a single RGB image i...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.