CNN-Based Denoising, Completion, and Prediction of Whole-Body Human-Depth Images

CNN-Based Denoising, Completion, and Prediction of Whole-Body Human-Depth Images

Three-dimensional human shape reconstruction is important in many applications, such as virtual or augmented reality (VR/AR), virtual clothing fitting, and healthcare. In this paper, we propose a learning-based method for reconstructing a whole-body point cloud from a single front-view human-depth i...

Full description

Bibliographic Details
Main Authors: Jae Won Jang, Young Chan Kwon, Hwasup Lim, Ouk Choi
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
3D human shape
convolutional neural networks
deep learning
single depth image
synthetic data generation
Online Access:https://ieeexplore.ieee.org/document/8924676/

Internet

https://ieeexplore.ieee.org/document/8924676/

Similar Items