3D Human Pose Regression using Graph Convolutional Network
- URL: http://arxiv.org/abs/2105.10379v1
- Date: Fri, 21 May 2021 14:41:31 GMT
- Title: 3D Human Pose Regression using Graph Convolutional Network
- Authors: Soubarna Banik, Alejandro Mendoza Gracia, Alois Knoll
- Abstract summary: We propose a graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses.
Our model's performance is close to the state-of-the-art, but with much fewer parameters.
- Score: 68.8204255655161
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 3D human pose estimation is a difficult task, due to challenges such as
occluded body parts and ambiguous poses. Graph convolutional networks encode
the structural information of the human skeleton in the form of an adjacency
matrix, which is beneficial for better pose prediction. We propose one such
graph convolutional network named PoseGraphNet for 3D human pose regression
from 2D poses. Our network uses an adaptive adjacency matrix and kernels
specific to neighbor groups. We evaluate our model on the Human3.6M dataset
which is a standard dataset for 3D pose estimation. Our model's performance is
close to the state-of-the-art, but with much fewer parameters. The model learns
interesting adjacency relations between joints that have no physical
connections, but are behaviorally similar.
Related papers
- MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose [20.099670445427964]
Reconstructing multi-human body mesh from a single monocular image is an important but challenging computer vision problem.
In this work, through a single graph neural network, we construct coherent multi-human meshes using only multi-human 2D pose as input.
arXiv Detail & Related papers (2022-05-25T08:54:52Z) - AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by
Learnable Motion Generation [24.009674750548303]
Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop.
We propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset.
Our method outperforms previous work in cross-dataset evaluations by 14% and previous semi-supervised learning methods that use partial 3D annotations by 16%.
arXiv Detail & Related papers (2021-12-22T00:27:52Z) - Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images [79.70127290464514]
We decompose the task into two stages, i.e. person localization and pose estimation.
And we propose three task-specific graph neural networks for effective message passing.
Our approach achieves state-of-the-art performance on CMU Panoptic and Shelf datasets.
arXiv Detail & Related papers (2021-09-13T11:44:07Z) - Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh
Recovery from a 2D Human Pose [70.23652933572647]
We propose a novel graph convolutional neural network (GraphCNN)-based system that estimates the 3D coordinates of human mesh vertices directly from the 2D human pose.
We show that our Pose2Mesh outperforms the previous 3D human pose and mesh estimation methods on various benchmark datasets.
arXiv Detail & Related papers (2020-08-20T16:01:56Z) - Unsupervised 3D Human Pose Representation with Viewpoint and Pose
Disentanglement [63.853412753242615]
Learning a good 3D human pose representation is important for human pose related tasks.
We propose a novel Siamese denoising autoencoder to learn a 3D pose representation.
Our approach achieves state-of-the-art performance on two inherently different tasks.
arXiv Detail & Related papers (2020-07-14T14:25:22Z) - Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image
Synthesis [72.34794624243281]
We propose a self-supervised learning framework to disentangle variations from unlabeled video frames.
Our differentiable formalization, bridging the representation gap between the 3D pose and spatial part maps, allows us to operate on videos with diverse camera movements.
arXiv Detail & Related papers (2020-04-09T07:55:01Z) - Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A
Geometric Approach [76.10879433430466]
We propose to estimate 3D human pose from multi-view images and a few IMUs attached at person's limbs.
It operates by firstly detecting 2D poses from the two signals, and then lifting them to the 3D space.
The simple two-step approach reduces the error of the state-of-the-art by a large margin on a public dataset.
arXiv Detail & Related papers (2020-03-25T00:26:54Z) - PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge
Distillation [6.023152721616894]
PoseNet3D takes 2D joints as input and outputs 3D skeletons and SMPL body model parameters.
We first train a teacher network that outputs 3D skeletons, using only 2D poses for training. The teacher network distills its knowledge to a student network that predicts 3D pose in SMPL representation.
Results on Human3.6M dataset for 3D human pose estimation demonstrate that our approach reduces the 3D joint prediction error by 18% compared to previous unsupervised methods.
arXiv Detail & Related papers (2020-03-07T00:10:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.