# DesigNet: Learning to Draw Vector Graphics as Designers Do

Source: [DesigNet: Learning to Draw Vector Graphics as Designers Do](<https://www.sota2.com/research/paper/69d732787d0172140ec76a82>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-10T05:00:04.898Z

Authors: Tomas Guija-Valiente, Iago Su\\'arez

Published: 2026-04-07T21:55:20.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Latin typeface generation (cross-reconstruction) on Proprietary Latin typeface dataset 52 letters (test)](<https://www.sota2.com/research/sota/latin-typeface-generation-cross-reconstruction-on-proprietary-latin-typeface-dataset-52-letters-test.md>): Latin typeface generation (cross-reconstruction); Proprietary Latin typeface dataset 52 letters (test); mIoU: 71.1.

- [Font Cross-Reconstruction on Chinese font dataset (cross-reconstruction protocol)](<https://www.sota2.com/research/sota/font-cross-reconstruction-on-chinese-font-dataset-cross-reconstruction-protocol.md>): Font Cross-Reconstruction; Chinese font dataset (cross-reconstruction protocol); IoU: 39.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.06494>)

[PDF](<https://arxiv.org/pdf/2604.06494.pdf>)