Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

08/16/2021
by   Ailing Zeng, et al.
0

Various deep learning techniques have been proposed to solve the single-view 2D-to-3D pose estimation problem. While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory. In this work, we target these hard poses and present a novel skeletal GNN learning solution. To be specific, we propose a hop-aware hierarchical channel-squeezing fusion layer to effectively extract relevant information from neighboring nodes while suppressing undesired noises in GNN learning. In addition, we propose a temporal-aware dynamic graph construction procedure that is robust and effective for 3D pose estimation. Experimental results on the Human3.6M dataset show that our solution achieves 10.3% average prediction accuracy improvement and greatly improves on hard poses over state-of-the-art techniques. We further apply the proposed technique on the skeleton-based action recognition task and also achieve state-of-the-art performance. Our code is available at https://github.com/ailingzengzzz/Skeletal-GNN.

READ FULL TEXT

page 2

page 7

research
03/17/2021

Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks

We propose a novel image based localization system using graph neural ne...
research
06/07/2021

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

Multi-person pose estimation and tracking serve as crucial steps for vid...
research
07/26/2020

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision

We present a novel end-to-end framework named as GSNet (Geometric and Sc...
research
11/02/2022

Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

6D object pose estimation aims to infer the relative pose between the ob...
research
04/06/2021

Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping

Bottom-up approaches for image-based multi-person pose estimation consis...
research
09/18/2023

Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation

The most commonly used method for addressing 3D geometric registration i...
research
10/11/2019

FetusMap: Fetal Pose Estimation in 3D Ultrasound

The 3D ultrasound (US) entrance inspires a multitude of automated prenat...

Please sign up or login with your details

Forgot password? Click here to reset