DesigNet: Learning to Draw Vector Graphics as Designers Do

TL;DR

DesigNet is a hierarchical Transformer-VAE model that generates editable SVG vector graphics with explicit continuity and alignment controls, bridging the gap between neural networks and human designers.

Contribution

It introduces differentiable modules for continuity and alignment refinement, enabling more accurate and editable SVG outputs for design workflows.

Findings

Achieves higher accuracy in continuity and alignment compared to state-of-the-art methods.

Produces SVG outlines that are easier to refine and integrate into professional workflows.

Operates directly on SVG sequences with a continuous command parameterization.

Abstract

AI-driven content generation has made remarkable progress in recent years. However, neural networks and human designers operate in fundamentally different ways, making collaboration between them challenging. We address this gap for Scalable Vector Graphics (SVG) by equipping neural networks with tools commonly used by designers, such as axis alignment and explicit continuity control at command junctions. We introduce DesigNet, a hierarchical Transformer-VAE that operates directly on SVG sequences with a continuous command parameterization. Our main contributions are two differentiable modules: a continuity self-refinement module that predicts $C^0$, $G^1$, and $C^1$ continuity for each curve point and enforces it by modifying B\'ezier control points, and an alignment self-refinement module with snapping capabilities for horizontal or vertical lines. DesigNet produces editable outlines and achieves competitive results against state-of-the-art methods, with notably higher accuracy in continuity and alignment. These properties ensure the outputs are easier to refine and integrate into professional design workflows. Source Code: https://github.com/TomasGuija/DesigNet.