Skip to main navigation Skip to search Skip to main content

Weighted voxel: A novel voxel representation for 3D reconstruction

  • Haozhe Xie
  • , Hongxun Yao
  • , Xiaoshuai Sun
  • , Shangchen Zhou
  • , Xiaojun Tong
  • Harbin Institute of Technology

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

Abstract

3D reconstruction has been attracting increasing attention in the past few years. With the surge of deep neural networks, the performance of 3D reconstruction has been improved significantly. However, the voxel reconstructed by extant approaches usually contains lots of noise and leads to heavy computation. In this paper, we define a new voxel representation, named Weighted Voxel. It provides more abundant information, facilitating the subsequent learning and generalization steps. Unlike regular voxel which consists of zero-one, the proposed Weighted Voxel makes full use of the structure information of voxels. Experimental results demonstrate that Weighted Voxel not only performs better in reconstruction but also takes less time in training.

Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Internet Multimedia Computing and Service, ICIMCS 2018
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450365208
DOIs
StatePublished - 17 Aug 2018
Event10th International Conference on Internet Multimedia Computing and Service, ICIMCS 2018 - Nanjing, China
Duration: 17 Aug 201819 Aug 2018

Publication series

NameACM International Conference Proceeding Series

Conference

Conference10th International Conference on Internet Multimedia Computing and Service, ICIMCS 2018
Country/TerritoryChina
CityNanjing
Period17/08/1819/08/18

Keywords

  • 3D Reconstruction
  • Convolutional Neural Network
  • Long Short-Term Memory
  • Multi-view
  • Voxel

Fingerprint

Dive into the research topics of 'Weighted voxel: A novel voxel representation for 3D reconstruction'. Together they form a unique fingerprint.

Cite this