Tools

LEADER 03456cam a2200541 i 4500

001 on1523697292;

003 OCoLC;

005 20260724101645.0;

006 m o d ;

007 cr unu||||||||;

008 250616s2025 ncua obm 000 0 eng d;

035 a| (OCoLC)1523697292;

090 a| TA1637;

049 a| EREE;

100 1 a| Cansever, Ayberk,e| author.?| UNAUTHORIZED;

245 10 a| Improving segmented style transfer via blended partial convolution /c| by Ayberk Cansever.;

264 1 a| [Greenville, N.C.] :b| [East Carolina University],c| 2025.;

300 a| 1 online resource (61 pages) :b| illustrations (chiefly color);

336 a| textb| txt2| rdacontent;

337 a| computerb| c2| rdamedia;

338 a| online resourceb| cr2| rdacarrier;

347 a| text fileb| application/pdfc| 94.28 MB2| rda;

538 a| System requirements: Adobe Reader.;

538 a| Mode of access: World Wide Web.;

502 b| M.S.c| East Carolina Universityd| 2025.;

500 a| Presented to the Faculty of the Department of Computer Science.;

500 a| Advisor: David Hart;

500 a| Title from PDF t.p. (viewed July 15, 2026).;

520 3 a| Style transfer aims to render the content of an image in the style of another, but applying this technique to specific segments within an image poses significant challenges, particularly in achieving seamless integration between styled and non-styled regions. In this thesis, we explore potential improvements to segmented style transfer by introducing blended partial convolution into the processing pipeline. Specifically, we evaluate three techniques: replacing traditional style transfer mechanisms with partial convolution, incorporating mask dilation in partial convolution, and applying mask feathering both prior to encoding and within the decoder. Systematically assessing these methods identifies their contributions to enhancing the style adaptation within designated segments, reducing boundary artifacts, and improving overall visual coherence. Preliminary results indicate that these techniques collectively have the potential to offer a more refined tool for applications in digital art, augmented reality, and image editing. This work advances the field of style transfer by addressing key limitations in segmented applications and provides a foundation for future research in localized style adaptation.;

504 a| Includes bibliographical references.;

650 0 a| Image processing.=| ^A115874;

650 0 a| Deep learning (Machine learning)=| ^A1458889;

650 0 a| Computer programming.=| ^A33242;

653 a| Segmented Style Transfer;

653 a| Masking in Style Transfer;

653 a| Blended Partial Convolution;

653 a| Multi-Region Style Transfer;

856 40 z| Access via ScholarShipu| http://hdl.handle.net/10342/14029;

653 a| Seamless Integration of Multiple Styles;

700 1 a| Hart, David Marvin,e| degree supervisor.1| https://id.oclc.org/worldcat/entity/E39PCjwGMj9dMQRHwk6B3d7rFX=| ^A1488432;

710 2 a| East Carolina University.b| Department of Computer Science.?| UNAUTHORIZED;

949 o| wjh;

994 a| C0b| ERE;

596 a| 1 4;

998 a| 6584095;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6584095-1001l| JNETm| JOYNERr| Ys| Yt| JNE3ETDu| 6/16/2025x| ETDz| JERESOURCE;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6584095-2001l| HSLELECm| HSLr| Ys| Yt| HEETDu| 6/16/2025x| ETDz| HERESOURCE;

Improving segmented style transfer via blended partial convolution / by Ayberk Cansever.

Author/creator	Cansever, Ayberk author.
Other author	Hart, David Marvin, degree supervisor.
Other author	East Carolina University. Department of Computer Science.
Format	Theses and dissertations
Publication	[Greenville, N.C.] : [East Carolina University], 2025.
Description	1 online resource (61 pages) : illustrations (chiefly color)
Supplemental Content	Access via ScholarShip
Subjects	Image processing. Deep learning (Machine learning) Computer programming.

Summary	Style transfer aims to render the content of an image in the style of another, but applying this technique to specific segments within an image poses significant challenges, particularly in achieving seamless integration between styled and non-styled regions. In this thesis, we explore potential improvements to segmented style transfer by introducing blended partial convolution into the processing pipeline. Specifically, we evaluate three techniques: replacing traditional style transfer mechanisms with partial convolution, incorporating mask dilation in partial convolution, and applying mask feathering both prior to encoding and within the decoder. Systematically assessing these methods identifies their contributions to enhancing the style adaptation within designated segments, reducing boundary artifacts, and improving overall visual coherence. Preliminary results indicate that these techniques collectively have the potential to offer a more refined tool for applications in digital art, augmented reality, and image editing. This work advances the field of style transfer by addressing key limitations in segmented applications and provides a foundation for future research in localized style adaptation.
General note	Presented to the Faculty of the Department of Computer Science.
General note	Advisor: David Hart
General note	Title from PDF t.p. (viewed July 15, 2026).
Dissertation note	M.S. East Carolina University 2025.
Bibliography note	Includes bibliographical references.
Technical details	System requirements: Adobe Reader.
Technical details	Mode of access: World Wide Web.

Availability

Library	Location	Call Number	Status	Item Actions
	Electronic Resources	Access Content Online	✔ Available

Improving segmented style transfer via blended partial convolution / by Ayberk Cansever.

Click here for more information about this title

Availability