Least commitment, viewpoint-based, multi-view stereo

Xiaoyan Hu, Philippos Mordohai

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

38 Scopus citations

Abstract

We address the problem of large-scale 3D reconstruction from calibrated images relying on a viewpoint-based approach. The representation is in the form of a collection of depth maps, which are fused to blend consistent depth estimates and minimize violations of visibility constraints. We adopt a least commitment strategy by allowing multiple candidate depth values per pixel in the fusion process and deferring hard decisions as much as possible. To address the inevitable noise in the depth maps, we explicitly model its sources, namely mismatches and inaccurate 3D coordinate estimation via triangulation, by measuring two types of uncertainty and using the uncertainty estimates to guide the fusion process. To the best of our knowledge, this is the first attempt to model both geometric and correspondence uncertainty in the context of dense 3D reconstruction. We show quantitative results on datasets with ground truth that are competitive with the state of the art.

Original languageEnglish
Title of host publicationProceedings - 2nd Joint 3DIM/3DPVT Conference
Subtitle of host publication3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012
Pages531-538
Number of pages8
DOIs
StatePublished - 2012
Event2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012 - Zurich, Switzerland
Duration: 13 Oct 201215 Oct 2012

Publication series

NameProceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012

Conference

Conference2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012
Country/TerritorySwitzerland
CityZurich
Period13/10/1215/10/12

Keywords

  • 3D reconstruction
  • depth map fusion
  • stereo vision

Fingerprint

Dive into the research topics of 'Least commitment, viewpoint-based, multi-view stereo'. Together they form a unique fingerprint.

Cite this