DeepAI AI Chat
Log In Sign Up

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

by   Ailing Zeng, et al.

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


page 2

page 7


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

We propose a novel image based localization system using graph neural ne...

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

Multi-person pose estimation and tracking serve as crucial steps for vid...

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...

HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization

Current works on multi-person 3D pose estimation mainly focus on the est...

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

6D object pose estimation aims to infer the relative pose between the ob...

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

Bottom-up approaches for image-based multi-person pose estimation consis...

Context Modeling in 3D Human Pose Estimation: A Unified Perspective

Estimating 3D human pose from a single image suffers from severe ambigui...