A fast, accurate and complete 3D head mesh modeling system

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI:10.1109/ICDSP.2016.7868609

Jun Yu, Zengfu Wang

引用次数: 2

Abstract

A real-time 3D head mesh modeling system is proposed. Firstly, the mesh model of appearance is reconstructed from multi-view visible images based on inter-regional cooperative optimization and depth super-resolution. Secondly, the mesh model of internal articulators is constructed by Magnetic Resonance Imaging. Finally, the mesh model of internal articulators is integrated to that of appearance by interpolation. The experimental results demonstrate the effectiveness of the system for fast and accurate head mesh modeling applications.

查看原文本刊更多论文

一个快速，准确和完整的3D头部网格建模系统

提出了一种实时三维头部网格建模系统。首先，基于区域间协同优化和深度超分辨率，从多视角可见光图像重构外观网格模型;其次，利用磁共振成像技术建立内关节的网格模型;最后，通过插值将内部关节的网格模型整合到外观的网格模型中。实验结果表明，该系统能够实现快速、准确的头部网格建模。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2016 IEEE International Conference on Digital Signal Processing (DSP)

自引率

0.00%

发文量