How good MVSNets are at depth fusion

Oleg Voynov, Aleksander Safin, Savva Ignatiev, Evgeny Burnaev

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

Abstract

We study the effects of the additional input to deep multi-view stereo methods in the form of low-quality sensor depth. We modify two state-of-the-art deep multi-view stereo methods for using with the input depth. We show that the additional input depth may improve the quality of deep multi-view stereo.

Original languageEnglish
Title of host publication13th International Conference on Machine Vision, ICMV 2020
EditorsWolfgang Osten, Dmitry P. Nikolaev, Jianhong Zhou
PublisherSPIE
ISBN (Electronic)9781510640405
DOIs
Publication statusPublished - 2020
Event13th International Conference on Machine Vision, ICMV 2020 - Rome, Italy
Duration: 2 Nov 20206 Nov 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11605
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference13th International Conference on Machine Vision, ICMV 2020
Country/TerritoryItaly
CityRome
Period2/11/206/11/20

Keywords

  • 3D reconstruction
  • Computer vision
  • Multi-view stereo

Fingerprint

Dive into the research topics of 'How good MVSNets are at depth fusion'. Together they form a unique fingerprint.

Cite this