MeshLifter: Weakly Supervised Approach for 3D Human Mesh Reconstruction from a Single 2D Pose Based on Loop Structure
In this paper, we address the problem of 3D human mesh reconstruction from a single 2D human pose based on deep learning. We propose MeshLifter, a network that estimates a 3D human mesh from an input 2D human pose. Unlike most existing 3D human mesh reconstruction studies that train models using pai...
Main Authors: | Sunwon Jeong, Ju Yong Chang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/15/4257 |
Similar Items
-
Attention-Based 3D Human Pose Sequence Refinement Network
by: Do-Yeop Kim, et al.
Published: (2021-07-01) -
Human-pose estimation based on weak supervision
by: Xiaoyan Hu, et al.
Published: (2023-08-01) -
Camera Motion Agnostic Method for Estimating 3D Human Poses
by: Seong Hyun Kim, et al.
Published: (2022-10-01) -
Deep Learning Methods for 3D Human Pose Estimation under Different Supervision Paradigms: A Survey
by: Dejun Zhang, et al.
Published: (2021-09-01) -
PosturePose: Optimized Posture Analysis for Semi-Supervised Monocular 3D Human Pose Estimation
by: Lawrence Amadi, et al.
Published: (2023-12-01)