Timothy Gerstner

timgerst at cs dot rutgers dot edu

MS Student

Computer Science

Rutgers University

Thesis

Pixelated Abstraction

Advisor:

Andrew Nealen
Pixel art remains a contemporary art form and a common rendering technique in digital games and media. However, the manual creation of pixel art is often time consuming and requires a degree of skill that is not easily obtained by novices of the art. In my thesis I present my work on automatically and semi-automatically converting high resolution images into an output that approximates the manual results of pixel artists. This is a multi-step, iterative algorithm that simultaneously solves for a palette and a mapping of segments of the input image to pixels in the output. The proposed tools gives the user flexible influence on the output and the ability to work anywhere between a purely automated and purely manual process.

[pdf] (20.3MB)

Publications

Pixelated Image Abstraction with Integrated User Constraints

Timothy Gerstner, Doug Decarlo, Marc Alexa, Adam Finkelstein, Yotam Gingold, Andrew Nealen. 2013. Computers & Graphics.

[preprint pdf] (11.1MB)

Pixelated Image Abstraction

Timothy Gerstner, Doug Decarlo, Marc Alexa, Adam Finkelstein, Yotam Gingold, Andrew Nealen. 2012. Proceedings of the International Symposium of Non-Photorealistic Animation and Rendering (NPAR)

[preprint pdf] (9.0MB)

Code

The source code for my research on Pixelated Abstraction can be found on github: https://github.com/timgerst/pix

I have also compiled the source (with interface) as a windows executable, which can be found here: [pix.zip] (1.1MB)
Please check the license and guide before using the interface.