期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 44, 期 3, 页码 1519-1533出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2020.3021023
关键词
Real-time 3D reconstruction; TSDF fusion; online texturing; SLAM; global consistency; CPU computing
资金
- Natural Science Foundation of China (NSFC) [61722209, 61860206003]
- Shenzhen Science and Technology Research and Development Funds [JCYJ20180507183706645, ZDYBH201900000002]
This paper presents an RGBD-based globally-consistent dense 3D reconstruction approach that allows real-time geometric reconstruction and texture mapping, achieving realistic visualization with compact memory consumption and low computational complexity.
High-quality reconstruction of 3D geometry and texture plays a vital role in providing immersive perception of the real world. Additionally, online computation enables the practical usage of 3D reconstruction for interaction. We present an RGBD-based globally-consistent dense 3D reconstruction approach, where high-quality (i.e., the spatial resolution of the RGB image) texture patches are mapped on high-resolution (<= 1 cm) geometric models online. The whole pipeline uses merely the CPU computing of a portable device. For real-time geometric reconstruction with online texturing, we propose to solve the texture optimization problem with a simplified incremental MRF solver in the context of geometric reconstruction pipeline using sparse voxel sampling strategy. An efficient reference-based color adjustment scheme is also proposed to achieve consistent texture patch colors under inconsistent luminance situations. Quantitative and qualitative experiments demonstrate that our online scheme achieves a realistic visualization of the environment with more abundant details, while taking fairly compact memory consumption and much lower computational complexity than existing solutions.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据