A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views

Amnon Shashua

doi:10.1109/WQV.1993.262944

A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views

Amnon Shashua^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

The author addresses the problem of reconstructing 3D space in a projective framework from two views, and the problem of artificially generating novel views of the scene from two given views. He shows that with the correspondences coming from four non-coplanar points in the scene and the corresponding epipoles, one can define and reconstruct (using simple linear methods) a projective invariant, referred to as projective depth, that can be used later to reconstruct the projective or affine structure of the scene, or directly to generate novel views of the scene. The derivation has the advantage that the viewing transformation matrix need not be recovered in the course of computations (i.e., he computes structure without motion).

Original language	English
Title of host publication	Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	107-117
Number of pages	11
ISBN (Electronic)	0818636920, 9780818636929
DOIs	https://doi.org/10.1109/WQV.1993.262944
State	Published - 1993
Externally published	Yes
Event	1993 IEEE Workshop on Qualitative Vision, WQV 1993 - New York, United States Duration: 14 Jun 1993 → …

Publication series

Name	Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993

Conference

Conference	1993 IEEE Workshop on Qualitative Vision, WQV 1993
Country/Territory	United States
City	New York
Period	14/06/93 → …

Bibliographical note

Publisher Copyright:
© 1993 IEEE.

Access to Document

10.1109/WQV.1993.262944

Cite this

Shashua, A. (1993). A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views. In Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993 (pp. 107-117). Article 262944 (Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WQV.1993.262944

@inproceedings{41666f2ef30d40eb95c8b36d4a48d228,

title = "A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views",

abstract = "The author addresses the problem of reconstructing 3D space in a projective framework from two views, and the problem of artificially generating novel views of the scene from two given views. He shows that with the correspondences coming from four non-coplanar points in the scene and the corresponding epipoles, one can define and reconstruct (using simple linear methods) a projective invariant, referred to as projective depth, that can be used later to reconstruct the projective or affine structure of the scene, or directly to generate novel views of the scene. The derivation has the advantage that the viewing transformation matrix need not be recovered in the course of computations (i.e., he computes structure without motion).",

author = "Amnon Shashua",

note = "Publisher Copyright: {\textcopyright} 1993 IEEE.; 1993 IEEE Workshop on Qualitative Vision, WQV 1993 ; Conference date: 14-06-1993",

year = "1993",

doi = "10.1109/WQV.1993.262944",

language = "אנגלית",

series = "Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "107--117",

booktitle = "Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993",

address = "ארצות הברית",

}

Shashua, A 1993, A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views. in Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993., 262944, Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993, Institute of Electrical and Electronics Engineers Inc., pp. 107-117, 1993 IEEE Workshop on Qualitative Vision, WQV 1993, New York, United States, 14/06/93. https://doi.org/10.1109/WQV.1993.262944

A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views. / Shashua, Amnon.
Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993. Institute of Electrical and Electronics Engineers Inc., 1993. p. 107-117 262944 (Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views

AU - Shashua, Amnon

PY - 1993

Y1 - 1993

N2 - The author addresses the problem of reconstructing 3D space in a projective framework from two views, and the problem of artificially generating novel views of the scene from two given views. He shows that with the correspondences coming from four non-coplanar points in the scene and the corresponding epipoles, one can define and reconstruct (using simple linear methods) a projective invariant, referred to as projective depth, that can be used later to reconstruct the projective or affine structure of the scene, or directly to generate novel views of the scene. The derivation has the advantage that the viewing transformation matrix need not be recovered in the course of computations (i.e., he computes structure without motion).

AB - The author addresses the problem of reconstructing 3D space in a projective framework from two views, and the problem of artificially generating novel views of the scene from two given views. He shows that with the correspondences coming from four non-coplanar points in the scene and the corresponding epipoles, one can define and reconstruct (using simple linear methods) a projective invariant, referred to as projective depth, that can be used later to reconstruct the projective or affine structure of the scene, or directly to generate novel views of the scene. The derivation has the advantage that the viewing transformation matrix need not be recovered in the course of computations (i.e., he computes structure without motion).

UR - http://www.scopus.com/inward/record.url?scp=78649583702&partnerID=8YFLogxK

U2 - 10.1109/WQV.1993.262944

DO - 10.1109/WQV.1993.262944

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:78649583702

T3 - Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993

SP - 107

EP - 117

BT - Proceedings - IEEE Workshop on Qualitative Vision, WQV 1993

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1993 IEEE Workshop on Qualitative Vision, WQV 1993

Y2 - 14 June 1993

ER -

A geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this