Advancing Dense 3D Reconstruction of Non-rigid Scenes by Using a Moving Camera

使用移动相机推进非刚性场景的密集 3D 重建

• 批准号: DE140100180
• 负责人: Dr Yuchao Dai
• 金额: $ 27.57万
• 依托单位: The Australian National University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Early Career Researcher Award
• 财政年份: 2014
• 资助国家: 澳大利亚
• 起止时间: 2014-05-22 至 2018-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DE140100180
• 关键词: Advancing; Dense; 3D; Reconstruction; Non

This project will advance the fundamental research in geometric computer vision and develop a new framework for efficient dense three-dimensional reconstruction of non-rigid scenes by using a moving camera. It is expected that this project will bring about breakthroughs in geometric computer vision with many daily applications, including three-dimensional natural human-computer interaction, three-dimensional reconstruction from historical movies and three-dimensional realistic animations. Its outcomes will enable users to capture and manipulate their surrounding dynamic world in three-dimensions easily and conveniently. This project will alleviate many of the major difficulties (dense correspondences, long sequences, complex deformations) with conventional non-rigid reconstruction methods.

该项目将推进几何计算机视觉的基础研究，并开发一种新的框架，利用移动摄像机高效地实现非刚性场景的密集三维重建。预计该项目将带来几何计算机视觉的突破，并在许多日常应用中实现，包括三维自然人机交互、由历史电影进行三维重建和三维逼真动画。它的成果将使用户能够轻松方便地捕捉和操纵他们周围的三维动态世界。该项目将缓解传统非刚性重建方法的许多主要困难(密集对应、长序列、复杂变形)。