Skip to main navigation Skip to search Skip to main content

3D Voxel Reconstruction Based on Shape Layer

  • Linlin Tang*
  • , Shuaijie Shi
  • , Shiyu Qin
  • , Xin Huang
  • , Yijie Fan
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen

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

Abstract

3D reconstruction is a basic and important task in computer vision. The overall reconstruction quality evaluation of voxel based 3D reconstruc-tion method is not high currently. This paper mainly aims at the problem that the overall reconstruction quality evaluation of voxel based 3D reconstruction methods is not high. According to the good conversion relationship between shape layer and voxels, a new shape layer based 3D voxel recon-struction network is proposed to transform the prediction problem of 3D voxels into the prediction problem of 2D depth map. Experiments show that it is superior to other voxel based 3D reconstruction methods.

Original languageEnglish
Title of host publicationGenetic and Evolutionary Computing - Proceedings of the Fourteenth International Conference on Genetic and Evolutionary Computing, 2021
EditorsShu-Chuan Chu, Jerry Chun-Wei Lin, Jianpo Li, Jeng-Shyang Pan
PublisherSpringer Science and Business Media Deutschland GmbH
Pages306-315
Number of pages10
ISBN (Print)9789811684296
DOIs
StatePublished - 2022
Externally publishedYes
Event14th International Conference on Genetic and Evolutionary Computing, ICGEC 2021 - Jilin, China
Duration: 21 Oct 202123 Oct 2021

Publication series

NameLecture Notes in Electrical Engineering
Volume833 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference14th International Conference on Genetic and Evolutionary Computing, ICGEC 2021
Country/TerritoryChina
CityJilin
Period21/10/2123/10/21

Keywords

  • 3D reconstruction
  • Neural network
  • Shape layer

Fingerprint

Dive into the research topics of '3D Voxel Reconstruction Based on Shape Layer'. Together they form a unique fingerprint.

Cite this