In this section, we explore four practical applications of IconShop: icon editing, icon interpolation, icon semantic combination, and icon design auto-suggestion.

To help you out, I cre-ated this icon design guide that will answer all the questions you might have along the way. The guide consists of three chapters, each covering a separate important topic that you …

We have conducted extensive experiments on vector font and icon datasets to show that our model can capture high-quality representation information and outperform the previous state-of-the-art on …

The vector glyph mapping technique essentially associates a vector glyph, or vector icon, with every sample point of the vector dataset. Various properties of the icon, such as location, direction, …

Generative models for vector graphics could serve as powerful tools, allowing artists to generate, manipulate, and animate vector graphics, potentially enhancing their creativity and productivity.

Vector graphics can be scaled to any size, and are compact. We show that a text-conditioned diffusion model trained on pixel representations of images can be used to generate SVG-exportable vector …

Vector icons generated with text prompts. The proposed IconShop supports icon synthesis from keywords (left three columns) and natural phrases and sentences (right three columns). Scalable …