An Efficient 3D Human Pose Retrieval and Reconstruction from 2D Image-Based Landmarks

An Efficient 3D Human Pose Retrieval and Reconstruction from 2D Image-Based Landmarks

We propose an efficient and novel architecture for 3D articulated human pose retrieval and reconstruction from 2D landmarks extracted from a 2D synthetic image, an annotated 2D image, an <i>in-the-wild</i> real RGB image or even a hand-drawn sketch. Given 2D joint positions in a single i...

Full description

Bibliographic Details
Main Authors: Hashim Yasin, Björn Krüger
Format: Article
Language:English
Published: MDPI AG 2021-04-01
Series:Sensors
Subjects:
motion capture
feature sets
3D human pose retrieval
knowledge-base
3D articulated pose estimation
optimization
Online Access:https://www.mdpi.com/1424-8220/21/7/2415

Internet

https://www.mdpi.com/1424-8220/21/7/2415

Similar Items