Real-Time Globally Consistent Dense 3D Reconstruction With Online Texturing

Lei Han, Siyuan Gu, Dawei Zhong, Shuxue Quan, Lu FangIEEE TPAMI 2022 · OpenReview

Abstract

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 ($\leq 1\ \text{cm}$) 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.
BibTeX
@article{han2022real,
  author = {Lei Han and Siyuan Gu and Dawei Zhong and Shuxue Quan and Lu Fang},
  title = {{Real-Time Globally Consistent Dense 3D Reconstruction With Online Texturing}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2022},
  url = {https://openreview.net/forum?id=XamtENjIbe},
}

Loading related content...

Figure