Semi-supervised 3D Hand-Object Pose Estimation via Pose Dictionary Learning

07/16/2021
by   Zida Cheng, et al.
0

3D hand-object pose estimation is an important issue to understand the interaction between human and environment. Current hand-object pose estimation methods require detailed 3D labels, which are expensive and labor-intensive. To tackle the problem of data collection, we propose a semi-supervised 3D hand-object pose estimation method with two key techniques: pose dictionary learning and an object-oriented coordinate system. The proposed pose dictionary learning module can distinguish infeasible poses by reconstruction error, enabling unlabeled data to provide supervision signals. The proposed object-oriented coordinate system can make 3D estimations equivariant to the camera perspective. Experiments are conducted on FPHA and HO-3D datasets. Our method reduces estimation error by 19.5 straightforward use of labeled data on FPHA and outperforms several baseline methods. Extensive experiments also validate the robustness of the proposed method.

READ FULL TEXT
research
04/25/2016

Semi-supervised Dictionary Learning Based on Hilbert-Schmidt Independence Criterion

In this paper, a novel semi-supervised dictionary learning and sparse re...
research
04/14/2022

SemiMultiPose: A Semi-supervised Multi-animal Pose Estimation Framework

Multi-animal pose estimation is essential for studying animals' social b...
research
03/27/2023

Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training

Despite the significant progress that depth-based 3D hand pose estimatio...
research
06/10/2021

Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation

Hand pose estimation is difficult due to different environmental conditi...
research
04/10/2018

Learning Pose Specific Representations by Predicting Different Views

The labeled data required to learn pose estimation for articulated objec...
research
11/30/2021

Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation

To obtain 3D annotations, we are restricted to controlled environments o...
research
11/14/2022

Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images

We study the problem of estimating 3D shape and pose of an object in ter...

Please sign up or login with your details

Forgot password? Click here to reset