Tools

LEADER 03025cam a2200529 i 4500

001 on1523697805;

003 OCoLC;

005 20260817102620.0;

006 m o d ;

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

008 250616s2025 ncua obm 000 0 eng d;

035 a| (OCoLC)1523697805;

090 a| T385;

049 a| EREE;

100 1 a| DuSablon, Raphael,e| author.;

245 10 a| Sampling and selection methods for applying 2D neural networks to 3D Gaussian splats /c| by Raphael DuSablon.;

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

300 a| 1 online resource (57 pages) :b| color illustrations;

336 a| textb| txt2| rdacontent;

337 a| computerb| c2| rdamedia;

338 a| online resourceb| cr2| rdacarrier;

347 a| text fileb| application/pdfc| 86.22 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 Data Science.;

500 a| Advisor: David Hart;

500 a| Title from PDF t.p. (viewed August 4, 2026).;

520 3 a| We propose a novel approach for applying interpolation methods to unstructured volumetric data that allows for the operation of 2D neural networks directly on 3D Gaussian splats. Gaussian splatting is at the cutting edge of volume rendering methods, 2D neural networks have achieved a dominant and lasting degree of success and real-life application. We propose leveraging the advantages of both, an approach which is the first of its kind. We extend the method for interpolated convolution on 3D surface meshes with 2D CNNs by Hart et al to the unstructured 3D volumetric data of Gaussian splats and present an end-to-end pipeline for our work. We showcase our results with style transfers on 3D Gaussian splats performed by a 2D convolution model with no retraining. Our results compare favorably with those of current approaches to performing style transfers on 3D Gaussians using purpose-built and purpose-trained 3D models.;

504 a| Includes bibliographical references.;

650 0 a| Rendering (Computer graphics);

650 0 a| Neural networks (Computer science);

650 0 a| Computer science.;

650 0 a| Computer algorithms.;

653 a| Gaussian Splat;

653 a| Interpolated Selectionconv;

653 a| Style Transfer;

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

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

856 40 z| Access via ScholarShipu| http://hdl.handle.net/10342/14084;

949 o| wjh;

994 a| C0b| ERE;

596 a| 1 4;

998 a| 6584110;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6584110-1001l| JNETm| JOYNERr| Ys| Yt| JNE3ETDu| 6/16/2025x| ETDz| JERESOURCE;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6584110-2001l| HSLELECm| HSLr| Ys| Yt| HEETDu| 6/16/2025x| ETDz| HERESOURCE;

Sampling and selection methods for applying 2D neural networks to 3D Gaussian splats / by Raphael DuSablon.

Author/creator	DuSablon, Raphael 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 (57 pages) : color illustrations
Supplemental Content	Access via ScholarShip
Subjects	Rendering (Computer graphics) Neural networks (Computer science) Computer science. Computer algorithms.

Summary	We propose a novel approach for applying interpolation methods to unstructured volumetric data that allows for the operation of 2D neural networks directly on 3D Gaussian splats. Gaussian splatting is at the cutting edge of volume rendering methods, 2D neural networks have achieved a dominant and lasting degree of success and real-life application. We propose leveraging the advantages of both, an approach which is the first of its kind. We extend the method for interpolated convolution on 3D surface meshes with 2D CNNs by Hart et al to the unstructured 3D volumetric data of Gaussian splats and present an end-to-end pipeline for our work. We showcase our results with style transfers on 3D Gaussian splats performed by a 2D convolution model with no retraining. Our results compare favorably with those of current approaches to performing style transfers on 3D Gaussians using purpose-built and purpose-trained 3D models.
General note	Presented to the Faculty of the Department of Data Science.
General note	Advisor: David Hart
General note	Title from PDF t.p. (viewed August 4, 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

Sampling and selection methods for applying 2D neural networks to 3D Gaussian splats / by Raphael DuSablon.

Click here for more information about this title

Availability