Appearance based object modeling using texture database: Acquisition, compression and rendering

R. Furukawa, Hiroshi Kawasaki, K. Ikeuchi, M. Sakauchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

61 Citations (Scopus)

Abstract

Image-based object modeling can be used to compose photorealistic images of modeled objects for various rendering conditions, such as viewpoint, light directions, etc. However, it is challenging to acquire the large number of object images required for all combinations of capturing parameters and to then handle the resulting huge data sets for the model. This paper presents a novel modeling method for acquiring and preserving appearances of objects. Using a specialized capturing platform, we first acquire objects' geometrical information and their complete 4D indexed texture sets, or bi-directional texture functions (BTF) in a highly automated manner Then we compress the acquired texture database using tensor product expansion. The compressed texture database facilitates rendering objects with arbitrary viewpoints, illumination, and deformation.

Original languageEnglish
Title of host publicationEurographics Workshop on Rendering
EditorsS. Gibson, P. Debevec, S.N. Spencer
Pages257-265
Number of pages9
Publication statusPublished - Dec 1 2002
Event13th Eurographics Workshop on Rendering - Pisa, Italy
Duration: Jun 26 2002Jun 28 2002

Publication series

NameEurographics Workshop on Rendering

Other

Other13th Eurographics Workshop on Rendering
CountryItaly
CityPisa
Period6/26/026/28/02

Fingerprint

Textures
Tensors
Lighting

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Furukawa, R., Kawasaki, H., Ikeuchi, K., & Sakauchi, M. (2002). Appearance based object modeling using texture database: Acquisition, compression and rendering. In S. Gibson, P. Debevec, & S. N. Spencer (Eds.), Eurographics Workshop on Rendering (pp. 257-265). (Eurographics Workshop on Rendering).

Appearance based object modeling using texture database : Acquisition, compression and rendering. / Furukawa, R.; Kawasaki, Hiroshi; Ikeuchi, K.; Sakauchi, M.

Eurographics Workshop on Rendering. ed. / S. Gibson; P. Debevec; S.N. Spencer. 2002. p. 257-265 (Eurographics Workshop on Rendering).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Furukawa, R, Kawasaki, H, Ikeuchi, K & Sakauchi, M 2002, Appearance based object modeling using texture database: Acquisition, compression and rendering. in S Gibson, P Debevec & SN Spencer (eds), Eurographics Workshop on Rendering. Eurographics Workshop on Rendering, pp. 257-265, 13th Eurographics Workshop on Rendering, Pisa, Italy, 6/26/02.
Furukawa R, Kawasaki H, Ikeuchi K, Sakauchi M. Appearance based object modeling using texture database: Acquisition, compression and rendering. In Gibson S, Debevec P, Spencer SN, editors, Eurographics Workshop on Rendering. 2002. p. 257-265. (Eurographics Workshop on Rendering).
Furukawa, R. ; Kawasaki, Hiroshi ; Ikeuchi, K. ; Sakauchi, M. / Appearance based object modeling using texture database : Acquisition, compression and rendering. Eurographics Workshop on Rendering. editor / S. Gibson ; P. Debevec ; S.N. Spencer. 2002. pp. 257-265 (Eurographics Workshop on Rendering).
@inproceedings{37c6d9e4174045a183c40e8d36c015d5,
title = "Appearance based object modeling using texture database: Acquisition, compression and rendering",
abstract = "Image-based object modeling can be used to compose photorealistic images of modeled objects for various rendering conditions, such as viewpoint, light directions, etc. However, it is challenging to acquire the large number of object images required for all combinations of capturing parameters and to then handle the resulting huge data sets for the model. This paper presents a novel modeling method for acquiring and preserving appearances of objects. Using a specialized capturing platform, we first acquire objects' geometrical information and their complete 4D indexed texture sets, or bi-directional texture functions (BTF) in a highly automated manner Then we compress the acquired texture database using tensor product expansion. The compressed texture database facilitates rendering objects with arbitrary viewpoints, illumination, and deformation.",
author = "R. Furukawa and Hiroshi Kawasaki and K. Ikeuchi and M. Sakauchi",
year = "2002",
month = "12",
day = "1",
language = "English",
isbn = "1581135343",
series = "Eurographics Workshop on Rendering",
pages = "257--265",
editor = "S. Gibson and P. Debevec and S.N. Spencer",
booktitle = "Eurographics Workshop on Rendering",

}

TY - GEN

T1 - Appearance based object modeling using texture database

T2 - Acquisition, compression and rendering

AU - Furukawa, R.

AU - Kawasaki, Hiroshi

AU - Ikeuchi, K.

AU - Sakauchi, M.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - Image-based object modeling can be used to compose photorealistic images of modeled objects for various rendering conditions, such as viewpoint, light directions, etc. However, it is challenging to acquire the large number of object images required for all combinations of capturing parameters and to then handle the resulting huge data sets for the model. This paper presents a novel modeling method for acquiring and preserving appearances of objects. Using a specialized capturing platform, we first acquire objects' geometrical information and their complete 4D indexed texture sets, or bi-directional texture functions (BTF) in a highly automated manner Then we compress the acquired texture database using tensor product expansion. The compressed texture database facilitates rendering objects with arbitrary viewpoints, illumination, and deformation.

AB - Image-based object modeling can be used to compose photorealistic images of modeled objects for various rendering conditions, such as viewpoint, light directions, etc. However, it is challenging to acquire the large number of object images required for all combinations of capturing parameters and to then handle the resulting huge data sets for the model. This paper presents a novel modeling method for acquiring and preserving appearances of objects. Using a specialized capturing platform, we first acquire objects' geometrical information and their complete 4D indexed texture sets, or bi-directional texture functions (BTF) in a highly automated manner Then we compress the acquired texture database using tensor product expansion. The compressed texture database facilitates rendering objects with arbitrary viewpoints, illumination, and deformation.

UR - http://www.scopus.com/inward/record.url?scp=0036980209&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036980209&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036980209

SN - 1581135343

T3 - Eurographics Workshop on Rendering

SP - 257

EP - 265

BT - Eurographics Workshop on Rendering

A2 - Gibson, S.

A2 - Debevec, P.

A2 - Spencer, S.N.

ER -