Acquiring axially-symmetric transparent objects using single-view transmission imaging
File(s)1314.pdf (7.45 MB)
Accepted version
Author(s)
Kim, J
Reshetouski, I
Ghosh, A
Type
Conference Paper
Abstract
We propose a novel, practical solution for high quality reconstruction of axially-symmetric transparent objects. While a special case, such transparent objects are ubiquitous in the real world. Common examples of these are glasses, goblets, tumblers, carafes, etc., that can have very unique and visually appealing forms making their reconstruction interesting for vision and graphics applications. Our acquisition setup involves imaging such objects from a single viewpoint while illuminating them from directly behind with a few patterns emitted by an LCD panel. Our reconstruction step is then based on optimization of the objects geometry and its refractive index to minimize the difference between observed and simulated transmission/refraction of rays passing through the object. We exploit the objects axial symmetry as a strong shape prior which allows us to achieve robust reconstruction from a single viewpoint using a simple, commodity acquisition setup. We demonstrate high quality reconstruction of several common rotationally symmetric as well as more complex n-fold symmetric transparent objects with our approach.
Date Issued
2017-11-09
Date Acceptance
2017-03-18
Citation
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp.1484-1492
ISBN
9781538604571
ISSN
1063-6919
Publisher
IEEE
Start Page
1484
End Page
1492
Journal / Book Title
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor
Engineering & Physical Science Research Council (EPSRC)
The Royal Society
Grant Number
EP/N006259/1
WM 120040
Source
30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Computer Science
Engineering
SHAPE
Publication Status
Published
Start Date
2017-06-21
Finish Date
2017-06-26
Coverage Spatial
Honolulu, Hawaii
Date Publish Online
2017-11-09