skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: GPU-based Scalable Volumetric Reconstruction for Multi-view Stereo

Abstract

We present a new scalable volumetric reconstruction algorithm for multi-view stereo using a graphics processing unit (GPU). It is an effectively parallelized GPU algorithm that simultaneously uses a large number of GPU threads, each of which performs voxel carving, in order to integrate depth maps with images from multiple views. Each depth map, triangulated from pair-wise semi-dense correspondences, represents a view-dependent surface of the scene. This algorithm also provides scalability for large-scale scene reconstruction in a high resolution voxel grid by utilizing streaming and parallel computation. The output is a photo-realistic 3D scene model in a volumetric or point-based representation. We demonstrate the effectiveness and the speed of our algorithm with a synthetic scene and real urban/outdoor scenes. Our method can also be integrated with existing multi-view stereo algorithms such as PMVS2 to fill holes or gaps in textureless regions.

Authors:
; ;
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1035961
Report Number(s):
LLNL-CONF-500954
TRN: US201205%%515
DOE Contract Number:  
W-7405-ENG-48
Resource Type:
Conference
Resource Relation:
Conference: Presented at: IVCNZ 2011 : Twenty-sixth International Conference Image and Vision Computing New Zealand, Auckland, New Zealand, Nov 29 - Dec 01, 2011
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICAL METHODS AND COMPUTING; ALGORITHMS; COMPUTERS; PROCESSING; RESOLUTION; VELOCITY; VISION

Citation Formats

Kim, H, Duchaineau, M, and Max, N. GPU-based Scalable Volumetric Reconstruction for Multi-view Stereo. United States: N. p., 2011. Web.
Kim, H, Duchaineau, M, & Max, N. GPU-based Scalable Volumetric Reconstruction for Multi-view Stereo. United States.
Kim, H, Duchaineau, M, and Max, N. Wed . "GPU-based Scalable Volumetric Reconstruction for Multi-view Stereo". United States. https://www.osti.gov/servlets/purl/1035961.
@article{osti_1035961,
title = {GPU-based Scalable Volumetric Reconstruction for Multi-view Stereo},
author = {Kim, H and Duchaineau, M and Max, N},
abstractNote = {We present a new scalable volumetric reconstruction algorithm for multi-view stereo using a graphics processing unit (GPU). It is an effectively parallelized GPU algorithm that simultaneously uses a large number of GPU threads, each of which performs voxel carving, in order to integrate depth maps with images from multiple views. Each depth map, triangulated from pair-wise semi-dense correspondences, represents a view-dependent surface of the scene. This algorithm also provides scalability for large-scale scene reconstruction in a high resolution voxel grid by utilizing streaming and parallel computation. The output is a photo-realistic 3D scene model in a volumetric or point-based representation. We demonstrate the effectiveness and the speed of our algorithm with a synthetic scene and real urban/outdoor scenes. Our method can also be integrated with existing multi-view stereo algorithms such as PMVS2 to fill holes or gaps in textureless regions.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2011},
month = {9}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: