A neural network scheme for transparent surface modelling

Mohamad Ivan Fanany, Itsuo Kumazawa, Kiichi Kobayashi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

This paper presents a new neural network (NN) scheme for recovering three dimensional (3D) transparent surface. We view the transparent surface modeling, not as a separate problem, but as an extension of opaque surface modeling. The main insight of this work is we simulate transparency not only for generating visually realistic images, but for recovering the object shape. We construct a formulation of transparent surface modeling using ray tracing framework into our NN. We compared this ray tracing method, with a texture mapping method that simultaneously map the silhouette images and smooth shaded images (obtained form our NN), and textured images (obtained from the teacher image) to an initial 3D model. By minimizing the images error between the output images of our NN and the teacher images, observed in multiple views, we refine vertices position of the initial 3D model. We show that our NN can refine the initial 3D model obtained by polarization images and converge into more accurate surface.

Original languageEnglish
Title of host publicationProceedings - GRAPHITE 2005 - 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia
Pages433-437
Number of pages5
DOIs
Publication statusPublished - 1 Dec 2005
EventGRAPHITE 2005 - 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia - Dunedin, New Zealand
Duration: 29 Nov 20052 Dec 2005

Publication series

NameProceedings - GRAPHITE 2005 - 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia

Conference

ConferenceGRAPHITE 2005 - 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia
CountryNew Zealand
CityDunedin
Period29/11/052/12/05

Keywords

  • 3D modeling
  • Neural network
  • Transparent surface

Fingerprint Dive into the research topics of 'A neural network scheme for transparent surface modelling'. Together they form a unique fingerprint.

Cite this