Cargando…
HUMANNET—A Two-Tiered Deep Neural Network Architecture for Self-Occluding Humanoid Pose Reconstruction
Majority of current research focuses on a single static object reconstruction from a given pointcloud. However, the existing approaches are not applicable to real world applications such as dynamic and morphing scene reconstruction. To solve this, we propose a novel two-tiered deep neural network ar...
Autores principales: | Kulikajevas, Audrius, Maskeliunas, Rytis, Damasevicius, Robertas, Scherer, Rafal |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8229438/ https://www.ncbi.nlm.nih.gov/pubmed/34201039 http://dx.doi.org/10.3390/s21123945 |
Ejemplares similares
-
Auto-Refining Reconstruction Algorithm for Recreation of Limited Angle Humanoid Depth Data
por: Kulikajevas, Audrius, et al.
Publicado: (2021) -
Reconstruction of 3D Object Shape Using Hybrid Modular Neural Network Architecture Trained on 3D Models from ShapeNetCore Dataset
por: Kulikajevas, Audrius, et al.
Publicado: (2019) -
Detection of sitting posture using hierarchical image composition and deep learning
por: Kulikajevas, Audrius, et al.
Publicado: (2021) -
3D Object Reconstruction from Imperfect Depth Data Using Extended YOLOv3 Network
por: Kulikajevas, Audrius, et al.
Publicado: (2020) -
Lightweight Deep Learning Model for Assessment of Substitution Voicing and Speech after Laryngeal Carcinoma Surgery
por: Maskeliūnas, Rytis, et al.
Publicado: (2022)