Low-poly image stylization

Thitiwudh Uasmith, Tantikorn Pukkaman, Sripian Peeraya

Research output: Contribution to journalArticle

Abstract

A low-poly image is a minimalist style of art that is currently widely used. It is an image derived from low-polygon 3D objects with an idea of image non-photorealistic abstraction. The trend of using low-poly images has accelerated rapidly since the introduction of vector images. Because low-poly images are based on vectors, the images are compact, scalable, editable, and easy to animate. Although semi-automatic low-poly image conversion tools exist, the resulting graphic generated from the tool does not resemble the original image in terms of its global structure. This paper presents an application that automatically creates a low-poly image that preserves global details, such as edges. Given a raster image, our algorithm automatically computes the polygons that best approximate the image. Our proposed algorithm is mainly based on K-means segmentation, contour extraction, the Ramer-Douglas-Peucker simplification, and the Delaunay triangulation. The output image is in a vector file format that can be easily further manipulated. For evaluation purposes, we distributed questionnaires to 30 participants that were comprised of 30 low-poly image sets; each set contained a low-poly image generated using our method and one generated using another method. From the experiment, we found that the majority of participants preferred the low-poly images generated using our method.

Original languageEnglish
Pages (from-to)131-139
Number of pages9
JournalJournal for Geometry and Graphics
Volume21
Issue number1
Publication statusPublished - 2017 Jan 1
Externally publishedYes

Fingerprint

Triangulation
Experiments

Keywords

  • Image abstraction
  • Image triangulation
  • Image vectorization
  • Low-poly image

ASJC Scopus subject areas

  • Applied Psychology
  • Geometry and Topology
  • Applied Mathematics

Cite this

Uasmith, T., Pukkaman, T., & Peeraya, S. (2017). Low-poly image stylization. Journal for Geometry and Graphics, 21(1), 131-139.

Low-poly image stylization. / Uasmith, Thitiwudh; Pukkaman, Tantikorn; Peeraya, Sripian.

In: Journal for Geometry and Graphics, Vol. 21, No. 1, 01.01.2017, p. 131-139.

Research output: Contribution to journalArticle

Uasmith, T, Pukkaman, T & Peeraya, S 2017, 'Low-poly image stylization', Journal for Geometry and Graphics, vol. 21, no. 1, pp. 131-139.
Uasmith T, Pukkaman T, Peeraya S. Low-poly image stylization. Journal for Geometry and Graphics. 2017 Jan 1;21(1):131-139.
Uasmith, Thitiwudh ; Pukkaman, Tantikorn ; Peeraya, Sripian. / Low-poly image stylization. In: Journal for Geometry and Graphics. 2017 ; Vol. 21, No. 1. pp. 131-139.
@article{4df1e848e457470ba1e17fa9c86262e3,
title = "Low-poly image stylization",
abstract = "A low-poly image is a minimalist style of art that is currently widely used. It is an image derived from low-polygon 3D objects with an idea of image non-photorealistic abstraction. The trend of using low-poly images has accelerated rapidly since the introduction of vector images. Because low-poly images are based on vectors, the images are compact, scalable, editable, and easy to animate. Although semi-automatic low-poly image conversion tools exist, the resulting graphic generated from the tool does not resemble the original image in terms of its global structure. This paper presents an application that automatically creates a low-poly image that preserves global details, such as edges. Given a raster image, our algorithm automatically computes the polygons that best approximate the image. Our proposed algorithm is mainly based on K-means segmentation, contour extraction, the Ramer-Douglas-Peucker simplification, and the Delaunay triangulation. The output image is in a vector file format that can be easily further manipulated. For evaluation purposes, we distributed questionnaires to 30 participants that were comprised of 30 low-poly image sets; each set contained a low-poly image generated using our method and one generated using another method. From the experiment, we found that the majority of participants preferred the low-poly images generated using our method.",
keywords = "Image abstraction, Image triangulation, Image vectorization, Low-poly image",
author = "Thitiwudh Uasmith and Tantikorn Pukkaman and Sripian Peeraya",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "21",
pages = "131--139",
journal = "Journal for Geometry and Graphics",
issn = "1433-8157",
publisher = "Heldermann Verlag",
number = "1",

}

TY - JOUR

T1 - Low-poly image stylization

AU - Uasmith, Thitiwudh

AU - Pukkaman, Tantikorn

AU - Peeraya, Sripian

PY - 2017/1/1

Y1 - 2017/1/1

N2 - A low-poly image is a minimalist style of art that is currently widely used. It is an image derived from low-polygon 3D objects with an idea of image non-photorealistic abstraction. The trend of using low-poly images has accelerated rapidly since the introduction of vector images. Because low-poly images are based on vectors, the images are compact, scalable, editable, and easy to animate. Although semi-automatic low-poly image conversion tools exist, the resulting graphic generated from the tool does not resemble the original image in terms of its global structure. This paper presents an application that automatically creates a low-poly image that preserves global details, such as edges. Given a raster image, our algorithm automatically computes the polygons that best approximate the image. Our proposed algorithm is mainly based on K-means segmentation, contour extraction, the Ramer-Douglas-Peucker simplification, and the Delaunay triangulation. The output image is in a vector file format that can be easily further manipulated. For evaluation purposes, we distributed questionnaires to 30 participants that were comprised of 30 low-poly image sets; each set contained a low-poly image generated using our method and one generated using another method. From the experiment, we found that the majority of participants preferred the low-poly images generated using our method.

AB - A low-poly image is a minimalist style of art that is currently widely used. It is an image derived from low-polygon 3D objects with an idea of image non-photorealistic abstraction. The trend of using low-poly images has accelerated rapidly since the introduction of vector images. Because low-poly images are based on vectors, the images are compact, scalable, editable, and easy to animate. Although semi-automatic low-poly image conversion tools exist, the resulting graphic generated from the tool does not resemble the original image in terms of its global structure. This paper presents an application that automatically creates a low-poly image that preserves global details, such as edges. Given a raster image, our algorithm automatically computes the polygons that best approximate the image. Our proposed algorithm is mainly based on K-means segmentation, contour extraction, the Ramer-Douglas-Peucker simplification, and the Delaunay triangulation. The output image is in a vector file format that can be easily further manipulated. For evaluation purposes, we distributed questionnaires to 30 participants that were comprised of 30 low-poly image sets; each set contained a low-poly image generated using our method and one generated using another method. From the experiment, we found that the majority of participants preferred the low-poly images generated using our method.

KW - Image abstraction

KW - Image triangulation

KW - Image vectorization

KW - Low-poly image

UR - http://www.scopus.com/inward/record.url?scp=85021837878&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021837878&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85021837878

VL - 21

SP - 131

EP - 139

JO - Journal for Geometry and Graphics

JF - Journal for Geometry and Graphics

SN - 1433-8157

IS - 1

ER -