Cargando…
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 in-the-wild real RGB image or even a hand-drawn sketch. Given 2D joint positions in a single image, we devise a d...
Autores principales: | Yasin, Hashim, Krüger, Björn |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8038066/ https://www.ncbi.nlm.nih.gov/pubmed/33915719 http://dx.doi.org/10.3390/s21072415 |
Ejemplares similares
-
An Effective and Efficient Approach for 3D Recovery of Human Motion Capture Data
por: Yasin, Hashim, et al.
Publicado: (2023) -
Reconstructing 3D human pose and shape from a single image and sparse IMUs
por: Liao, Xianhua, et al.
Publicado: (2023) -
Filtered pose graph for efficient kinect pose reconstruction
por: Plantard, Pierre, et al.
Publicado: (2016) -
Pose ResNet: 3D Human Pose Estimation Based on Self-Supervision
por: Bao, Wenxia, et al.
Publicado: (2023) -
Head Pose Estimation through Keypoints Matching between Reconstructed 3D Face Model and 2D Image
por: Liu, Leyuan, et al.
Publicado: (2021)