Super resolving texture mapping from multiple view images for 3D model construction

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

There are wide varieties of applications of 3D modeling from real images, which can generate virtual view images by rendering the input images onto the 3D shape model. Because the virtual viewpoint is not generally at the same point, the synthesized image at virtual view does not have sufficient resolution. For improving this resolution problem, we propose a method for improving the rendered texture resolution. For each vertex of the 3D shape model, the position of the vertex is adjusted for improving the texture of the neighboring triangle patches. For the improvement, the position of vertex is adjusted by comparing the observation (input image) with projected image of model texture. Repeating the visit of every vertex, not only super resolved texture but also more accurate 3D patch model can be obtained. By performing the experiments using synthesized multiple view images of 51 calibrated cameras around the object scene and real VTR image sequence, it is demonstrated that the proposed method can successfully provide super resolved texture image with improved shape 3D model.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Pages1418-1421
Number of pages4
Volume2
Publication statusPublished - 2000
Event2000 IEEE Interantional Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: 2000 Oct 82000 Oct 11

Other

Other2000 IEEE Interantional Conference on Systems, Man and Cybernetics
CityNashville, TN, USA
Period00/10/800/10/11

Fingerprint

Textures
Cameras
Experiments

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Saito, H. (2000). Super resolving texture mapping from multiple view images for 3D model construction. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 2, pp. 1418-1421). IEEE.

Super resolving texture mapping from multiple view images for 3D model construction. / Saito, Hideo.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2 IEEE, 2000. p. 1418-1421.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Saito, H 2000, Super resolving texture mapping from multiple view images for 3D model construction. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 2, IEEE, pp. 1418-1421, 2000 IEEE Interantional Conference on Systems, Man and Cybernetics, Nashville, TN, USA, 00/10/8.
Saito H. Super resolving texture mapping from multiple view images for 3D model construction. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2. IEEE. 2000. p. 1418-1421
Saito, Hideo. / Super resolving texture mapping from multiple view images for 3D model construction. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2 IEEE, 2000. pp. 1418-1421
@inproceedings{1e054b75f76f459c8538a9f43a6f3208,
title = "Super resolving texture mapping from multiple view images for 3D model construction",
abstract = "There are wide varieties of applications of 3D modeling from real images, which can generate virtual view images by rendering the input images onto the 3D shape model. Because the virtual viewpoint is not generally at the same point, the synthesized image at virtual view does not have sufficient resolution. For improving this resolution problem, we propose a method for improving the rendered texture resolution. For each vertex of the 3D shape model, the position of the vertex is adjusted for improving the texture of the neighboring triangle patches. For the improvement, the position of vertex is adjusted by comparing the observation (input image) with projected image of model texture. Repeating the visit of every vertex, not only super resolved texture but also more accurate 3D patch model can be obtained. By performing the experiments using synthesized multiple view images of 51 calibrated cameras around the object scene and real VTR image sequence, it is demonstrated that the proposed method can successfully provide super resolved texture image with improved shape 3D model.",
author = "Hideo Saito",
year = "2000",
language = "English",
volume = "2",
pages = "1418--1421",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Super resolving texture mapping from multiple view images for 3D model construction

AU - Saito, Hideo

PY - 2000

Y1 - 2000

N2 - There are wide varieties of applications of 3D modeling from real images, which can generate virtual view images by rendering the input images onto the 3D shape model. Because the virtual viewpoint is not generally at the same point, the synthesized image at virtual view does not have sufficient resolution. For improving this resolution problem, we propose a method for improving the rendered texture resolution. For each vertex of the 3D shape model, the position of the vertex is adjusted for improving the texture of the neighboring triangle patches. For the improvement, the position of vertex is adjusted by comparing the observation (input image) with projected image of model texture. Repeating the visit of every vertex, not only super resolved texture but also more accurate 3D patch model can be obtained. By performing the experiments using synthesized multiple view images of 51 calibrated cameras around the object scene and real VTR image sequence, it is demonstrated that the proposed method can successfully provide super resolved texture image with improved shape 3D model.

AB - There are wide varieties of applications of 3D modeling from real images, which can generate virtual view images by rendering the input images onto the 3D shape model. Because the virtual viewpoint is not generally at the same point, the synthesized image at virtual view does not have sufficient resolution. For improving this resolution problem, we propose a method for improving the rendered texture resolution. For each vertex of the 3D shape model, the position of the vertex is adjusted for improving the texture of the neighboring triangle patches. For the improvement, the position of vertex is adjusted by comparing the observation (input image) with projected image of model texture. Repeating the visit of every vertex, not only super resolved texture but also more accurate 3D patch model can be obtained. By performing the experiments using synthesized multiple view images of 51 calibrated cameras around the object scene and real VTR image sequence, it is demonstrated that the proposed method can successfully provide super resolved texture image with improved shape 3D model.

UR - http://www.scopus.com/inward/record.url?scp=0034499059&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034499059&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034499059

VL - 2

SP - 1418

EP - 1421

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -