Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation

01/24/2020
by   Yifei Chen, et al.
15

Hand pose estimation is more challenging than body pose estimation due to severe articulation, self-occlusion and high dexterity of the hand. Current approaches often rely on a popular body pose algorithm, such as the Convolutional Pose Machine (CPM), to learn 2D keypoint features. These algorithms cannot adequately address the unique challenges of hand pose estimation, because they are trained solely based on keypoint positions without seeking to explicitly model structural relationship between them. We propose a novel Nonparametric Structure Regularization Machine (NSRM) for 2D hand pose estimation, adopting a cascade multi-task architecture to learn hand structure and keypoint representations jointly. The structure learning is guided by synthetic hand mask representations, which are directly computed from keypoint positions, and is further strengthened by a novel probabilistic representation of hand limbs and an anatomically inspired composition strategy of mask synthesis. We conduct extensive studies on two public datasets - OneHand 10k and CMU Panoptic Hand. Experimental results demonstrate that explicitly enforcing structure learning consistently improves pose estimation accuracy of CPM baseline models, by 1.17 The implementation and experiment code is freely available online. Our proposal of incorporating structural learning to hand pose estimation requires no additional training information, and can be a generic add-on module to other pose estimation models.

READ FULL TEXT

page 3

page 4

page 8

research
11/24/2019

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

We rethink a well-know bottom-up approach for multi-person pose estimati...
research
11/28/2019

An End-to-end Framework for Unconstrained Monocular 3D Hand Pose Estimation

This work addresses the challenging problem of unconstrained 3D hand pos...
research
07/21/2022

Pose for Everything: Towards Category-Agnostic Pose Estimation

Existing works on 2D pose estimation mainly focus on a certain category,...
research
02/05/2020

Rotation-invariant Mixed Graphical Model Network for 2D Hand Pose Estimation

In this paper, we propose a new architecture named Rotation-invariant Mi...
research
09/21/2023

Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views

We present Ego3DPose, a highly accurate binocular egocentric 3D pose rec...
research
11/11/2021

Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation

While hand pose estimation is a critical component of most interactive e...
research
09/12/2019

Efficient 2.5D Hand Pose Estimation via Auxiliary Multi-Task Training for Embedded Devices

2D Key-point estimation is an important precursor to 3D pose estimation ...

Please sign up or login with your details

Forgot password? Click here to reset