# Teaching GANs to Sketch in Vector Format

arXiv: https://arxiv.org/abs/1904.03620 · HTML: https://mlsanity.com/paper/1904.03620/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [CLIPasso: Semantically-Aware Object Sketching](https://mlsanity.com/paper/2202.05822/) (2022)
- [Differentiable Drawing and Sketching](https://mlsanity.com/paper/2103.16194/) (2021)
- [DoodleFormer: Creative Sketch Drawing with Transformers](https://mlsanity.com/paper/2112.03258/) (2021)
- [SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation](https://mlsanity.com/paper/2502.08642/) (2025)
- [SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation](https://mlsanity.com/paper/2308.14191/) (2023)
- [Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool](https://mlsanity.com/paper/2111.14934/) (2021)
- [ViSketch-GPT: Collaborative Multi-Scale Feature Extraction for Sketch Recognition and Generation](https://mlsanity.com/paper/2503.22374/) (2025)
- [Single-Line Drawing Generation via Semantics-Driven Optimization](https://mlsanity.com/paper/2606.01910/) (2026)

## Abstract (arXiv)

Sketching is more fundamental to human cognition than speech. Deep Neural Networks (DNNs) have achieved the state-of-the-art in speech-related tasks but have not made significant development in generating stroke-based sketches a.k.a sketches in vector format. Though there are Variational Auto Encoders (VAEs) for generating sketches in vector format, there is no Generative Adversarial Network (GAN) architecture for the same. In this paper, we propose a standalone GAN architecture SkeGAN and a VAE-GAN architecture VASkeGAN, for sketch generation in vector format. SkeGAN is a stochastic policy in Reinforcement Learning (RL), capable of generating both multidimensional continuous and discrete outputs. VASkeGAN hybridizes a VAE and a GAN, in order to couple the efficient representation of data by VAE with the powerful generating capabilities of a GAN, to produce visually appealing sketches. We also propose a new metric called the Ske-score which quantifies the quality of vector sketches. We have validated that SkeGAN and VASkeGAN generate visually appealing sketches by using Human Turing Test and Ske-score.