By-Example Synthesis of Vector Textures

TL;DR

This paper introduces a novel method for synthesizing large vector textures from a single raster example by segmenting, clustering, and using neighborhood descriptors to generate consistent, scalable vector textures.

Contribution

It presents a new approach combining segmentation, clustering, neighborhood descriptors, and gradient fields for vector texture synthesis from a single exemplar.

Findings

Effective synthesis of arbitrarily large vector textures.

Uses perceptual metrics to evaluate quality.

Produces visually consistent and scalable textures.

Abstract

We propose a new method for synthesizing an arbitrarily sized novel vector texture given a single raster exemplar. Our method first segments the exemplar to extract the primary textons, and then clusters them based on visual similarity. We then compute a descriptor to capture each texton's neighborhood which contains the inter-category relationships that are used at synthesis time. Next, we use a simple procedure to both extract and place the secondary textons behind the primary polygons. Finally, our method constructs a gradient field for the background which is defined by a set of data points and colors. The color of the secondary polygons are also adjusted to better match the gradient field. To compare our work with other methods, we use a wide range of perceptual-based metrics.