2026-09-18T21:32:23Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1196922026-06-06T00:54:23Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Frédo Durand. Zhong, Kimberli Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2018-12-18T19:46:01Z 2018-12-18T19:46:01Z 2018 2018 http://hdl.handle.net/1721.1/119692 1078149677 Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 67-68). Today, designers work in tandem with computerized tools to create stylized graphic designs, diagrams, and icons. In this work, we explore the applications of generative modeling to the design of vectorized drawings, with a focus on font glyphs. We establish a data-driven approach for creating preliminary graphics upon which designers can iterate. To accomplish this, we present an end-to-end pipeline for a supervised training system on Scalable Vector Graphics (SVGs) that learns to reconstruct training data and produce similar but novel examples. We demonstrate its results on selected characters using a Google Fonts dataset of 2552 font faces. Our approach uses a variational autoencoder to learn sequences of SVG drawing commands and is capable of both recreating ground truth inputs and generating unseen, editable SVG outputs. To investigate improvements to model performance, we perform two experiments: one on the effects of various SVG feature encodings on generated outputs, and one on a modified architecture that explicitly encodes style and class separately for multi-class generation. by Kimberli Zhong. M.Eng. 68 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Learning to draw vector graphics : applying generative modeling to font glyphs Applying generative modeling to font glyphs Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="606f3da9-f2d9-4630-a10f-4828b47f933c"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Learning to draw vector graphics : applying generative modeling to font glyphs</Title> <Subtitle>Applying generative modeling to font glyphs</Subtitle> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2018</PublicationDate> <Authors> <Author> <DisplayName>Zhong, Kimberli</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>Today, designers work in tandem with computerized tools to create stylized graphic designs, diagrams, and icons. In this work, we explore the applications of generative modeling to the design of vectorized drawings, with a focus on font glyphs. We establish a data-driven approach for creating preliminary graphics upon which designers can iterate. To accomplish this, we present an end-to-end pipeline for a supervised training system on Scalable Vector Graphics (SVGs) that learns to reconstruct training data and produce similar but novel examples. We demonstrate its results on selected characters using a Google Fonts dataset of 2552 font faces. Our approach uses a variational autoencoder to learn sequences of SVG drawing commands and is capable of both recreating ground truth inputs and generating unseen, editable SVG outputs. To investigate improvements to model performance, we perform two experiments: one on the effects of various SVG feature encodings on generated outputs, and one on a modified architecture that explicitly encodes style and class separately for multi-class generation.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>