3D Human Pose Estimation Using Möbius Graph Convolutional Networks

03/20/2022
by   Niloofar Azizi, et al.
0

3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph convolutional networks (GCNs), which achieve state-of-the-art performance and provide rather light-weight architectures. However, a major limitation of GCNs is their inability to encode all the transformations between joints explicitly. To address this issue, we propose a novel spectral GCN using the Möbius transformation (MöbiusGCN). In particular, this allows us to directly and explicitly encode the transformation between joints, resulting in a significantly more compact representation. Compared to even the lightest architectures so far, our novel approach requires 90-98 our lightest MöbiusGCN uses only 0.042M trainable parameters. Besides the drastic parameter reduction, explicitly encoding the transformation of joints also enables us to achieve state-of-the-art results. We evaluate our approach on the two challenging pose estimation benchmarks, Human3.6M and MPI-INF-3DHP, demonstrating both state-of-the-art results and the generalization capabilities of MöbiusGCN.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/21/2021

3D Human Pose Regression using Graph Convolutional Network

3D human pose estimation is a difficult task, due to challenges such as ...
research
10/16/2021

Joint 3D Human Shape Recovery from A Single Imag with Bilayer-Graph

The ability to estimate the 3D human shape and pose from images can be u...
research
04/06/2019

Semantic Graph Convolutional Networks for 3D Human Pose Regression

In this paper, we study the problem of learning Graph Convolutional Netw...
research
07/23/2015

Human Pose Estimation with Iterative Error Feedback

Hierarchical feature extractors such as Convolutional Networks (ConvNets...
research
08/31/2016

Human Pose Estimation in Space and Time using 3D CNN

This paper explores the capabilities of convolutional neural networks to...
research
02/25/2020

Toward fast and accurate human pose estimation via soft-gated skip connections

This paper is on highly accurate and highly efficient human pose estimat...
research
02/13/2023

Capsules as viewpoint learners for human pose estimation

The task of human pose estimation (HPE) deals with the ill-posed problem...

Please sign up or login with your details

Forgot password? Click here to reset