HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation
This addresses the problem of real-time hand-object pose estimation for applications like human-computer interaction, though it appears incremental as it builds on existing graph-based methods.
The paper tackles hand-object pose estimation by proposing HOPE-Net, a lightweight model that uses adaptive graph convolutional neural networks to jointly estimate 2D and 3D poses in real-time, achieving better accuracy in both 2D and 3D coordinate estimation through end-to-end training.
Hand-object pose estimation (HOPE) aims to jointly detect the poses of both a hand and of a held object. In this paper, we propose a lightweight model called HOPE-Net which jointly estimates hand and object pose in 2D and 3D in real-time. Our network uses a cascade of two adaptive graph convolutional neural networks, one to estimate 2D coordinates of the hand joints and object corners, followed by another to convert 2D coordinates to 3D. Our experiments show that through end-to-end training of the full network, we achieve better accuracy for both the 2D and 3D coordinate estimation problems. The proposed 2D to 3D graph convolution-based model could be applied to other 3D landmark detection problems, where it is possible to first predict the 2D keypoints and then transform them to 3D.