Presentation 1998/3/20
Curved Shape Estimetion From Single-Eye Real-Images Using Network Inversion Technique
Hiroki KUBO, Keisuke KAMEYAMA, Yukio KOSUGI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We discuss the inverse problem of estimating 3D shape of an object from single-eyed 2D images. First we evaluated the deformation by calculating the set of shifting vectors. These vectors were applied to an inversion network to estimate the 3D surface. For improving the ill-posedness while solving the inverse problem by the network inversion technique, the concept of regularization was successfully introduced to yield the solution from surface pattern such as random dots or the texture on the surface.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) network inversion / inverse theory / regularization / Shape-from-Texture / surface-form estimation
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/3/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Curved Shape Estimetion From Single-Eye Real-Images Using Network Inversion Technique
Sub Title (in English)
Keyword(1) network inversion
Keyword(2) inverse theory
Keyword(3) regularization
Keyword(4) Shape-from-Texture
Keyword(5) surface-form estimation
1st Author's Name Hiroki KUBO
1st Author's Affiliation Interdisciplinary Graduate School of Science and Engneering, Tokyo Institute of Technology()
2nd Author's Name Keisuke KAMEYAMA
2nd Author's Affiliation Interdisciplinary Graduate School of Science and Engneering, Tokyo Institute of Technology
3rd Author's Name Yukio KOSUGI
3rd Author's Affiliation Interdisciplinary Graduate School of Science and Engneering, Tokyo Institute of Technology
Date 1998/3/20
Paper #
Volume (vol) vol.97
Number (no) 624
Page pp.pp.-
#Pages 8
Date of Issue