TY - GEN
T1 - A neural network scheme for transparent surface modelling
AU - Fanany, Mohamad Ivan
AU - Kumazawa, Itsuo
AU - Kobayashi, Kiichi
PY - 2005
Y1 - 2005
N2 - 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.
AB - 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.
KW - 3D modeling
KW - Neural network
KW - Transparent surface
UR - http://www.scopus.com/inward/record.url?scp=33745844052&partnerID=8YFLogxK
U2 - 10.1145/1101389.1101475
DO - 10.1145/1101389.1101475
M3 - Conference contribution
AN - SCOPUS:33745844052
SN - 1595932267
SN - 9781595932266
T3 - Proceedings - GRAPHITE 2005 - 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia
SP - 433
EP - 437
BT - Proceedings - GRAPHITE 2005 - 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia
T2 - GRAPHITE 2005 - 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia
Y2 - 29 November 2005 through 2 December 2005
ER -