High-Quality Surface-Based 3D Reconstruction Using 2.5D Maps

Lingxiao Song*, Xiao Yu, Huijun Di, Weiran Wang

*Corresponding author for this work

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

Abstract

Previous works on RGB-D reconstruction are based on voxels, points, or meshes, which are either too computationally expensive to represent high-resolution 3D models, or not convenient for model regularization to deal with noise and errors. In this paper, we propose a new method to reconstruct 3D models with more accurate geometric information and better texture. Our method uses abstract surfaces consisting of different points with similar information as units of the model. To reduce the complexity, we use 2.5D heightmaps to represent each surface in the reconstructed model, making it convenient to do regularization. Experiments demonstrate the effectiveness of our method.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages758-759
Number of pages2
ISBN (Electronic)9781665484022
DOIs
Publication statusPublished - 2022
Event2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022 - Virtual, Online, New Zealand
Duration: 12 Mar 202216 Mar 2022

Publication series

NameProceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022

Conference

Conference2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022
Country/TerritoryNew Zealand
CityVirtual, Online
Period12/03/2216/03/22

Keywords

  • Human computer interaction
  • Human-centered computing
  • Human-centered computing
  • Virtual reality
  • Visualization
  • Visualization design and evaluation methods

Fingerprint

Dive into the research topics of 'High-Quality Surface-Based 3D Reconstruction Using 2.5D Maps'. Together they form a unique fingerprint.

Cite this

Song, L., Yu, X., Di, H., & Wang, W. (2022). High-Quality Surface-Based 3D Reconstruction Using 2.5D Maps. In Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022 (pp. 758-759). (Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VRW55335.2022.00230