HKUST Institutional Repository >
Computer Science and Engineering >
CSE Conference Papers >
Please use this identifier to cite or link to this item:
|Title: ||3-D reconstruction of multipart self-occluding objects|
|Authors: ||Jojic, Nebojsa|
Shen, Helen C.
|Keywords: ||Multipart objects|
|Issue Date: ||Jan-1998 |
|Citation: ||The Third Asian Conference on Computer Vision (ACCV), Hong Kong, Jan. 1998, p. 455-462|
|Abstract: ||In this paper we present a method for reconstruction of multipart objects from several arbitrary views using deformable superquadrics as the models of the object's parts. Two visual cues are used: occluding contours and stereo (possibly aided by projected patterns). The object can be relatively complex and can exhibit numerous self occlusions from some or all views. Our preliminary experiments on a human body and a tailor's mannequin show that the reconstruction is more complete than in purely stereo or structured light based methods and more precise than the reconstruction from occluding contours only.|
|Rights: ||The original publication of the article may be found from the publisher's website http://www.springerlink.com/.|
|Appears in Collections:||CSE Conference Papers|
Files in This Item:
|1_13D.pdf||pre-published version||866Kb||Adobe PDF||View/Open|
All items in this Repository are protected by copyright, with all rights reserved.