DesigNet: Learning to Draw Vector Graphics as Designers Do

Tomas Guija-Valiente; Iago Suárez

cs.CVApr 7, 2026

DesigNet: Learning to Draw Vector Graphics as Designers Do

Authors: Tomas Guija-Valiente, Iago Suárez

Organizations: Machine Learning Circle, Spain · Universidad Politécnica de Madrid, Departamento de Inteligencia Artificial, Spain · Qualcomm XR Labs, Spain

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 Bézier 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.

Figures & tables

Figure 1: Overview of DesigNet . A subset of characters ("H", "a", "m", "b", "u", "r", …) from a font is encoded to extract style features. The decoder then generates the remaining glyphs by combining the learned style with the embedding of the target letters. Finally, our self-refinement modules adjust control points and endpoints to enhance continuity and axis alignment, yielding cleaner SVG outputs.

Figure 2: Illustration of different continuity types .

C^{0}

: only geometric continuity,

G^{1}

: collinear tangents, and

C^{1}

: collinear tangents with equal magnitude.

Figure 3: Examples of Continuity and Alignment Modules . We show the predicted glyphs before and after the self-refinement modules.

\mathtt{LineFromTo}

commands are shown in blue and

\mathtt{CurveFromTo}

commands in green. The predicted continuity is represented by the pink squares, circles, and diamonds. We highlight with orange arrows the junctions corrected by the Self-refinement modules based on the pink predictions.

Figure 4: Qualitative comparison of reconstructed words using Latin fonts . The first row presents the ground truth (GT) glyphs, including their joints and control points. The second and third rows compare the outputs of DeepSVG and DesigNet against the GT, where black indicates overlapping regions, green denotes GT regions not covered by the prediction, and red marks predicted regions that do not correspond to the GT.

Figure 5: Qualitative comparison of reconstructed words using Chinese fonts .

Model	IoU $\uparrow$	L1 $\downarrow$	RE $\downarrow$	Cont. Acc. $\uparrow$	Align. Acc. $\uparrow$
DeepSVG	0.789	0.069	8.782	0.567	0.603
+ cont. args., +sin. pos. enc., +centered glyphs	0.943	0.016	2.242	0.567	0.368
+ hierarchical latent space	0.963	0.010	1.477	0.651	0.380
+ relaxed rep. and aux. loss	0.970	0.009	1.137	0.686	0.376
+ self-refinement 75% Conf. Trh.	0.969	0.009	1.138	0.886	0.969

Table 1: Ablation study of our VAE model on the test split of our proprietary dataset. Using continuous drawing parameters instead of the quantized representation in DeepSVG leads to a substantial improvement in reconstruction quality. Subsequent architectural enhancements further increase reconstruction fidelity, while the continuity and alignment self-refinement modules markedly improve continuity and alignment accuracy.

Figure 6: Font Interpolation : Examples of latent space interpolation in DesigNet between two fonts with different weights and slants.

Figure 7: Qualitative comparison of icon reconstructions : Each pair shows ground truth (GT) and our generated glyph.

Model	IoU $\uparrow$	L1 $\downarrow$	RE $\downarrow$	Cont. Acc. $\uparrow$	Align. Acc. $\uparrow$
DualVector [ 17 ]	0.564	0.137	-	-	-
DeepVecFont-v2 [ 31 ]	0.681	0.117	13.124	0.444	0.391
DeepVecFont-v2 + Self-Ref.	0.675	0.120	13.269	0.528	0.391
DesigNet w/o Self-Ref.	0.711	0.106	12.665	0.276	0.282
DesigNet	0.693	0.115	13.126	0.482	0.531
DeepVecFont-v2 10 shots	0.735	0.091	11.848	0.452	0.383

Table 2: Comparison on our proprietary dataset for Latin typeface generation (52 letters) on the cross-reconstruction task.

Figure 8: Reconstruction quality across encoding (left) and decoding (right) glyph sets. From top to bottom: ground truth (GT), DeepVecFont-v2, and our method after refinement.

Model	IoU $\uparrow$	L1 $\downarrow$	RE $\downarrow$	Cont. Acc. $\uparrow$	Align. Acc. $\uparrow$
DeepVecFont-v2 [ 31 ]	0.380	0.216	21.414	0.499	0.198
DeepVecFont-v2 + Self-Ref.	0.378	0.218	21.423	0.501	0.205
DesigNet w/o Self-Ref.	0.397	0.219	19.604	0.501	0.247
DesigNet	0.391	0.221	19.651	0.512	0.351
DeepVecFont-v2 10 shots	0.417	0.199	20.211	0.498	0.202

Table 3: Comparison on the Chinese font dataset [ 31 ] . Metrics are computed on the cross-reconstruction task.

Vector Graphics Generation

See all 26 papers

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Apr 6, 2026Ximing Xing, Ziteng Xue, Zhenxi Li +8Vector Graphics Generation Visual Tokenization
Tencent · Visual Computing Group, Beijing
DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model
Sep 28, 2026Shurui Liu, Weide Chen, Changwang Yi +1Vector Graphics Generation Generative Modeling
School of Computer Science and Engineering, Sun Yat-sen University, China · School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, China
Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs
Aug 26, 2026Matthew Perlman, James Beetham, Niels Da Vitoria Lobo +2Vector Graphics Generation VLM Adaptation
University of Massachusetts Amherst · University of Central Florida

Apr 6, 2026J/K move · Enter open · S save

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

Ximing Xing, Ziteng Xue, Zhenxi Li, Weicong Liang+7

Tencent · Visual Computing Group, Beijing

Vector Graphics Generation Visual Tokenization Text-to-SVG Generation Visual Token Compression

Open paper AskPDF arXiv

Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, existing approaches still rely on generic byte-level tokenization inherited from natural language processing, which poorly reflects the geometric structure of vector graphics. Numerical coordinates are fragmented into discrete symbols, destroying spatial relationships and introducing severe token redundancy, often leading to coordinate hallucination and inefficient long-sequence generation. To address these challenges, we propose HiVG, a hierarchical SVG tokenization framework tailored for autoregressive vector graphics generation. HiVG decomposes raw SVG strings into structured atomic tokens and further compresses executable command--parameter groups into geometry-constrained segment tokens, substantially improving sequence efficiency while preserving syntactic validity. To further mitigate spatial mismatch, we introduce a Hierarchical Mean--Noise (HMN) initialization strategy that injects numerical ordering signals and semantic priors into new token embeddings. Combined with a curriculum training paradigm that progressively increases program complexity, HiVG enables more stable learning of executable SVG programs. Extensive experiments on both text-to-SVG and image-to-SVG tasks demonstrate improved generation fidelity, spatial consistency, and sequence efficiency compared with conventional tokenization schemes. Our code is publicly available at https://github.com/ximinng/HiVG

Abstract

Vector Graphics Generation

Explore similar work

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model

Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs