Mesh Deformation Scheme for High Quality 3D Model Reconstruction

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

1 Scopus citations

Abstract

This paper proposes a new mesh deformation scheme in a 3D reconstruction in which the performance deteriorates when an object of an unlearned category is input in a 3D model generation network. The proposed method uses a new loss function to generate appropriate 3D reconstruction outputs even for inputs of unlearned categories of 3D models. We compare the performance with the existing method so as to prove the validity of this method. The simulation results show that the proposed loss function improves the generalization ability of the 3D reconstruction with good performance even for inputs of unlearned categories.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages728-730
Number of pages3
ISBN (Electronic)9798350333336
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023 - Kyoto, Japan
Duration: 26 Jun 202328 Jun 2023

Publication series

NameProceedings - 2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023

Conference

Conference2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023
Country/TerritoryJapan
CityKyoto
Period26/06/2328/06/23

Keywords

  • 3D Mesh Model
  • 3D modeling
  • 3D Reconstruction

Fingerprint

Dive into the research topics of 'Mesh Deformation Scheme for High Quality 3D Model Reconstruction'. Together they form a unique fingerprint.

Cite this