3D reconstruction based on epipolar geometry

M. Kimura, Hideo Saito

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Recently, it becomes popular to synthesize new viewpoint images based on some sampled viewpoint images of real scene using technique of computer vision. 3D shape reconstruction in Euclidean space is not necessarily required, but information of dense matching points is basically enough to synthesize new viewpoint images. In this paper, we propose a new method for 3D reconstruction from three cameras based on projective geometry. In the proposed method, three input camera images are rectified based on projective geometry, so that the vertical and horizontal directions can be completely aligned with the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the directions of camera projection. Such alignment simplifies the procedure for projection between the 3D space and the image planes in PVS. Taking this advantage of PVS, silhouettes of the objects are projected into PVS, so that the searching area of matching points can be reduced. The consistency of color value between the images is also evaluated for final determination of the matching point. The finally acquired matching points in the proposed method are described as the surface of the objects in PVS. The acquired surface of the objects in PVS also includes knowledge about occlusion. Finally, images from new viewpoints can be synthesized from the matching points and occlusions. Although the proposed method requires only weak calibration, plausible occlusions are also synthesized in the images. In the experiments, images of virtual viewpoints, which were set among three cameras, are synthesized from three real images.

Original languageEnglish
Pages (from-to)1690-1697
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE84-D
Issue number12
Publication statusPublished - 2001 Dec

Fingerprint

Cameras
Geometry
Computer vision
Calibration
Color
Experiments

Keywords

  • Computer vision
  • Image processing
  • Projective geometry
  • Weak calibration

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

3D reconstruction based on epipolar geometry. / Kimura, M.; Saito, Hideo.

In: IEICE Transactions on Information and Systems, Vol. E84-D, No. 12, 12.2001, p. 1690-1697.

Research output: Contribution to journalArticle

@article{f488566cd88445fa8ea0252d0be4fdbd,
title = "3D reconstruction based on epipolar geometry",
abstract = "Recently, it becomes popular to synthesize new viewpoint images based on some sampled viewpoint images of real scene using technique of computer vision. 3D shape reconstruction in Euclidean space is not necessarily required, but information of dense matching points is basically enough to synthesize new viewpoint images. In this paper, we propose a new method for 3D reconstruction from three cameras based on projective geometry. In the proposed method, three input camera images are rectified based on projective geometry, so that the vertical and horizontal directions can be completely aligned with the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the directions of camera projection. Such alignment simplifies the procedure for projection between the 3D space and the image planes in PVS. Taking this advantage of PVS, silhouettes of the objects are projected into PVS, so that the searching area of matching points can be reduced. The consistency of color value between the images is also evaluated for final determination of the matching point. The finally acquired matching points in the proposed method are described as the surface of the objects in PVS. The acquired surface of the objects in PVS also includes knowledge about occlusion. Finally, images from new viewpoints can be synthesized from the matching points and occlusions. Although the proposed method requires only weak calibration, plausible occlusions are also synthesized in the images. In the experiments, images of virtual viewpoints, which were set among three cameras, are synthesized from three real images.",
keywords = "Computer vision, Image processing, Projective geometry, Weak calibration",
author = "M. Kimura and Hideo Saito",
year = "2001",
month = "12",
language = "English",
volume = "E84-D",
pages = "1690--1697",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "12",

}

TY - JOUR

T1 - 3D reconstruction based on epipolar geometry

AU - Kimura, M.

AU - Saito, Hideo

PY - 2001/12

Y1 - 2001/12

N2 - Recently, it becomes popular to synthesize new viewpoint images based on some sampled viewpoint images of real scene using technique of computer vision. 3D shape reconstruction in Euclidean space is not necessarily required, but information of dense matching points is basically enough to synthesize new viewpoint images. In this paper, we propose a new method for 3D reconstruction from three cameras based on projective geometry. In the proposed method, three input camera images are rectified based on projective geometry, so that the vertical and horizontal directions can be completely aligned with the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the directions of camera projection. Such alignment simplifies the procedure for projection between the 3D space and the image planes in PVS. Taking this advantage of PVS, silhouettes of the objects are projected into PVS, so that the searching area of matching points can be reduced. The consistency of color value between the images is also evaluated for final determination of the matching point. The finally acquired matching points in the proposed method are described as the surface of the objects in PVS. The acquired surface of the objects in PVS also includes knowledge about occlusion. Finally, images from new viewpoints can be synthesized from the matching points and occlusions. Although the proposed method requires only weak calibration, plausible occlusions are also synthesized in the images. In the experiments, images of virtual viewpoints, which were set among three cameras, are synthesized from three real images.

AB - Recently, it becomes popular to synthesize new viewpoint images based on some sampled viewpoint images of real scene using technique of computer vision. 3D shape reconstruction in Euclidean space is not necessarily required, but information of dense matching points is basically enough to synthesize new viewpoint images. In this paper, we propose a new method for 3D reconstruction from three cameras based on projective geometry. In the proposed method, three input camera images are rectified based on projective geometry, so that the vertical and horizontal directions can be completely aligned with the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the directions of camera projection. Such alignment simplifies the procedure for projection between the 3D space and the image planes in PVS. Taking this advantage of PVS, silhouettes of the objects are projected into PVS, so that the searching area of matching points can be reduced. The consistency of color value between the images is also evaluated for final determination of the matching point. The finally acquired matching points in the proposed method are described as the surface of the objects in PVS. The acquired surface of the objects in PVS also includes knowledge about occlusion. Finally, images from new viewpoints can be synthesized from the matching points and occlusions. Although the proposed method requires only weak calibration, plausible occlusions are also synthesized in the images. In the experiments, images of virtual viewpoints, which were set among three cameras, are synthesized from three real images.

KW - Computer vision

KW - Image processing

KW - Projective geometry

KW - Weak calibration

UR - http://www.scopus.com/inward/record.url?scp=0035679681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035679681&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0035679681

VL - E84-D

SP - 1690

EP - 1697

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 12

ER -