Skip to main navigation Skip to search Skip to main content

A Graph-based Error Correction Model Using Lie-algebraic Cohomology and Its Application on Global Consistent Indoor Scene Reconstruction

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a novel, effective method for global indoor scene reconstruction problems by geometric topology. Based on point cloud pairwise registration methods (e.g ICP) or IMU, we focus on the problem of accumulated error for the composition of transformations along any loops. The major technical contribution of this paper is a linear method for the graph optimation, using only solving a Poisson equation. We demonstrate the consistency of our method from Hodge-Helmhotz decomposition theorem and experiments on multiple RGBD datasets of indoor scene. The experimental results also demonstrate that our global registration method runs quickly and provides accurate reconstructions.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages869-870
Number of pages2
ISBN (Electronic)9798350348392
DOIs
StatePublished - 2023
Event2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023 - Shanghai, China
Duration: Mar 25 2023Mar 29 2023

Publication series

NameProceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023

Conference

Conference2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
Country/TerritoryChina
CityShanghai
Period03/25/2303/29/23

Keywords

  • 3D Scene Reconstruction
  • Human
  • Human-centered computing
  • Visualization
  • Visualization design and evaluation methods-Modeling and simulation
  • Visualization- Visu-alization techniques
  • centered computing

Fingerprint

Dive into the research topics of 'A Graph-based Error Correction Model Using Lie-algebraic Cohomology and Its Application on Global Consistent Indoor Scene Reconstruction'. Together they form a unique fingerprint.

Cite this