Pixelated image abstraction with integrated user constraints

Timothy Gerstner; Doug Decarlo; Marc Alexa; Adam Finkelstein; Yotam Gingold; Andrew Nealen

doi:10.1016/j.cag.2012.12.007

Pixelated image abstraction with integrated user constraints

Timothy Gerstner, Doug Decarlo, Marc Alexa, Adam Finkelstein, Yotam Gingold, Andrew Nealen

Research output: Contribution to journal › Article › peer-review

Abstract

We present an automatic method that can be used to abstract high resolution images into very low resolution outputs with reduced color palettes in the style of pixel art. Our method simultaneously solves for a mapping of features and a reduced palette needed to construct the output image. The results are an approximation to the results generated by pixel artists. We compare our method against the results of two naive methods common to image manipulation programs, as well as the hand-crafted work of pixel artists. Through a formal user study and interviews with expert pixel artists we show that our results offer an improvement over the naive methods. By integrating a set of manual controls into our algorithm, we give users the ability to add constraints and incorporate their own choices into the iterative process.

Original language	English (US)
Pages (from-to)	333-347
Number of pages	15
Journal	Computers and Graphics (Pergamon)
Volume	37
Issue number	5
DOIs	https://doi.org/10.1016/j.cag.2012.12.007
State	Published - 2013

Keywords

Color quantization
Image abstraction
Image segmentation
Non-photorealistic rendering
Pixel art

ASJC Scopus subject areas

General Engineering
Human-Computer Interaction
Computer Graphics and Computer-Aided Design

Access to Document

10.1016/j.cag.2012.12.007

Cite this

@article{70370dff636c47489ca52e76e868fc79,

title = "Pixelated image abstraction with integrated user constraints",

abstract = "We present an automatic method that can be used to abstract high resolution images into very low resolution outputs with reduced color palettes in the style of pixel art. Our method simultaneously solves for a mapping of features and a reduced palette needed to construct the output image. The results are an approximation to the results generated by pixel artists. We compare our method against the results of two naive methods common to image manipulation programs, as well as the hand-crafted work of pixel artists. Through a formal user study and interviews with expert pixel artists we show that our results offer an improvement over the naive methods. By integrating a set of manual controls into our algorithm, we give users the ability to add constraints and incorporate their own choices into the iterative process.",

keywords = "Color quantization, Image abstraction, Image segmentation, Non-photorealistic rendering, Pixel art",

author = "Timothy Gerstner and Doug Decarlo and Marc Alexa and Adam Finkelstein and Yotam Gingold and Andrew Nealen",

note = "Funding Information: We thank the anonymous reviewers for their helpful feedback. We also wish to thank pixel artists Craig Adams, Ted Martens, and Adam Saltsman for their advice and comments. This research is supported in part by the Sloan Foundation, the NSF (CAREER Award CCF-06-43268 and Grants IIS-09-16129 , IIS-10-48948 , IIS-11-17257 , CMMI-11-29917 , IIS-09-16845 , DGE-05-49115 ), and generous gifts from Adobe, Autodesk, Intel, mental images, Microsoft, NVIDIA, Side Effects Software, and the Walt Disney Company. The following copyrighted images are used with permission: Fig. 1 by Alice Bartlett, Fig. 9 by Louis Vest, Fig. 13 (giraffe) by Paul Adams, and Fig. 13 (pagoda) by William Warby. The pixel art in Fig. 12 is copyright Adam Saltsman (top) and Ted Martens (bottom). ",

year = "2013",

doi = "10.1016/j.cag.2012.12.007",

language = "English (US)",

volume = "37",

pages = "333--347",

journal = "Computers and Graphics (Pergamon)",

issn = "0097-8493",

publisher = "Elsevier Ltd",

number = "5",

}

TY - JOUR

T1 - Pixelated image abstraction with integrated user constraints

AU - Gerstner, Timothy

AU - Decarlo, Doug

AU - Alexa, Marc

AU - Finkelstein, Adam

AU - Gingold, Yotam

AU - Nealen, Andrew

N1 - Funding Information: We thank the anonymous reviewers for their helpful feedback. We also wish to thank pixel artists Craig Adams, Ted Martens, and Adam Saltsman for their advice and comments. This research is supported in part by the Sloan Foundation, the NSF (CAREER Award CCF-06-43268 and Grants IIS-09-16129 , IIS-10-48948 , IIS-11-17257 , CMMI-11-29917 , IIS-09-16845 , DGE-05-49115 ), and generous gifts from Adobe, Autodesk, Intel, mental images, Microsoft, NVIDIA, Side Effects Software, and the Walt Disney Company. The following copyrighted images are used with permission: Fig. 1 by Alice Bartlett, Fig. 9 by Louis Vest, Fig. 13 (giraffe) by Paul Adams, and Fig. 13 (pagoda) by William Warby. The pixel art in Fig. 12 is copyright Adam Saltsman (top) and Ted Martens (bottom).

PY - 2013

Y1 - 2013

N2 - We present an automatic method that can be used to abstract high resolution images into very low resolution outputs with reduced color palettes in the style of pixel art. Our method simultaneously solves for a mapping of features and a reduced palette needed to construct the output image. The results are an approximation to the results generated by pixel artists. We compare our method against the results of two naive methods common to image manipulation programs, as well as the hand-crafted work of pixel artists. Through a formal user study and interviews with expert pixel artists we show that our results offer an improvement over the naive methods. By integrating a set of manual controls into our algorithm, we give users the ability to add constraints and incorporate their own choices into the iterative process.

AB - We present an automatic method that can be used to abstract high resolution images into very low resolution outputs with reduced color palettes in the style of pixel art. Our method simultaneously solves for a mapping of features and a reduced palette needed to construct the output image. The results are an approximation to the results generated by pixel artists. We compare our method against the results of two naive methods common to image manipulation programs, as well as the hand-crafted work of pixel artists. Through a formal user study and interviews with expert pixel artists we show that our results offer an improvement over the naive methods. By integrating a set of manual controls into our algorithm, we give users the ability to add constraints and incorporate their own choices into the iterative process.

KW - Color quantization

KW - Image abstraction

KW - Image segmentation

KW - Non-photorealistic rendering

KW - Pixel art

UR - http://www.scopus.com/inward/record.url?scp=84876575584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876575584&partnerID=8YFLogxK

U2 - 10.1016/j.cag.2012.12.007

DO - 10.1016/j.cag.2012.12.007

M3 - Article

AN - SCOPUS:84876575584

SN - 0097-8493

VL - 37

SP - 333

EP - 347

JO - Computers and Graphics (Pergamon)

JF - Computers and Graphics (Pergamon)

IS - 5

ER -

Pixelated image abstraction with integrated user constraints

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this