Adaptive synthesis of distance fields

Sung Ho Lee, Taejung Park, Jong Hyun Kim, Chang-Hun Kim

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We address the computational resource requirements of 3D example-based synthesis with an adaptive synthesis technique that uses a tree-based synthesis map. A signed-distance field (SDF) is determined for the 3D exemplars, and then new models can be synthesized as SDFs by neighborhood matching. Unlike voxel synthesis approach, our input is posed in the real domain to preserve maximum detail. In comparison to straightforward extensions to the existing volume texture synthesis approach, we made several improvements in terms of memory requirements, computation times, and synthesis quality. The inherent parallelism in this method makes it suitable for a multicore CPU. Results show that computation times and memory requirements are very much reduced, and large synthesized scenes exhibit fine details which mimic the exemplars.

Original languageEnglish
Article number5975144
Pages (from-to)1135-1145
Number of pages11
JournalIEEE Transactions on Visualization and Computer Graphics
Volume18
Issue number7
DOIs
Publication statusPublished - 2012 Apr 17

Fingerprint

Data storage equipment
Program processors
Textures

Keywords

  • 3D shape synthesis
  • example-based synthesis

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Adaptive synthesis of distance fields. / Lee, Sung Ho; Park, Taejung; Kim, Jong Hyun; Kim, Chang-Hun.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 18, No. 7, 5975144, 17.04.2012, p. 1135-1145.

Research output: Contribution to journalArticle

Lee, Sung Ho ; Park, Taejung ; Kim, Jong Hyun ; Kim, Chang-Hun. / Adaptive synthesis of distance fields. In: IEEE Transactions on Visualization and Computer Graphics. 2012 ; Vol. 18, No. 7. pp. 1135-1145.
@article{b78168dccc014a4b92bb9b98841e5900,
title = "Adaptive synthesis of distance fields",
abstract = "We address the computational resource requirements of 3D example-based synthesis with an adaptive synthesis technique that uses a tree-based synthesis map. A signed-distance field (SDF) is determined for the 3D exemplars, and then new models can be synthesized as SDFs by neighborhood matching. Unlike voxel synthesis approach, our input is posed in the real domain to preserve maximum detail. In comparison to straightforward extensions to the existing volume texture synthesis approach, we made several improvements in terms of memory requirements, computation times, and synthesis quality. The inherent parallelism in this method makes it suitable for a multicore CPU. Results show that computation times and memory requirements are very much reduced, and large synthesized scenes exhibit fine details which mimic the exemplars.",
keywords = "3D shape synthesis, example-based synthesis",
author = "Lee, {Sung Ho} and Taejung Park and Kim, {Jong Hyun} and Chang-Hun Kim",
year = "2012",
month = "4",
day = "17",
doi = "10.1109/TVCG.2011.134",
language = "English",
volume = "18",
pages = "1135--1145",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "7",

}

TY - JOUR

T1 - Adaptive synthesis of distance fields

AU - Lee, Sung Ho

AU - Park, Taejung

AU - Kim, Jong Hyun

AU - Kim, Chang-Hun

PY - 2012/4/17

Y1 - 2012/4/17

N2 - We address the computational resource requirements of 3D example-based synthesis with an adaptive synthesis technique that uses a tree-based synthesis map. A signed-distance field (SDF) is determined for the 3D exemplars, and then new models can be synthesized as SDFs by neighborhood matching. Unlike voxel synthesis approach, our input is posed in the real domain to preserve maximum detail. In comparison to straightforward extensions to the existing volume texture synthesis approach, we made several improvements in terms of memory requirements, computation times, and synthesis quality. The inherent parallelism in this method makes it suitable for a multicore CPU. Results show that computation times and memory requirements are very much reduced, and large synthesized scenes exhibit fine details which mimic the exemplars.

AB - We address the computational resource requirements of 3D example-based synthesis with an adaptive synthesis technique that uses a tree-based synthesis map. A signed-distance field (SDF) is determined for the 3D exemplars, and then new models can be synthesized as SDFs by neighborhood matching. Unlike voxel synthesis approach, our input is posed in the real domain to preserve maximum detail. In comparison to straightforward extensions to the existing volume texture synthesis approach, we made several improvements in terms of memory requirements, computation times, and synthesis quality. The inherent parallelism in this method makes it suitable for a multicore CPU. Results show that computation times and memory requirements are very much reduced, and large synthesized scenes exhibit fine details which mimic the exemplars.

KW - 3D shape synthesis

KW - example-based synthesis

UR - http://www.scopus.com/inward/record.url?scp=84861460131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861460131&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2011.134

DO - 10.1109/TVCG.2011.134

M3 - Article

C2 - 21808095

AN - SCOPUS:84861460131

VL - 18

SP - 1135

EP - 1145

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 7

M1 - 5975144

ER -