# B'ezierSketch: A generative model for scalable vector sketches

arXiv: https://arxiv.org/abs/2007.02190 · HTML: https://mlsanity.com/paper/2007.02190/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2020.

## Built on by (most cited first, 30 of 43)

- [SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks](https://mlsanity.com/paper/2207.04632/) (2022)
- [CanvasVAE: Learning to Generate Vector Graphic Documents](https://mlsanity.com/paper/2108.01249/) (2021)
- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context](https://mlsanity.com/paper/2203.02113/) (2022)
- [SketchAgent: Language-Driven Sequential Sketch Generation](https://mlsanity.com/paper/2411.17673/) (2024)
- [De-rendering Stylized Texts](https://mlsanity.com/paper/2110.01890/) (2021)
- [Neural Face Identification in a 2D Wireframe Projection of a Manifold Object](https://mlsanity.com/paper/2203.04229/) (2022)
- [AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints](https://mlsanity.com/paper/2205.10636/) (2022)
- [Wired Perspectives: Multi-View Wire Art Embraces Generative AI](https://mlsanity.com/paper/2311.15421/) (2023)
- [Cloud2Curve: Generation and Vectorization of Parametric Sketches](https://mlsanity.com/paper/2103.15536/) (2021)
- [ChiroDiff: Modelling chirographic data with Diffusion Models](https://mlsanity.com/paper/2304.03785/) (2023)
- [SketchINR: A First Look into Sketches as Implicit Neural Representations](https://mlsanity.com/paper/2403.09344/) (2024)
- [Everything's Talkin': Pareidolia Face Reenactment](https://mlsanity.com/paper/2104.03061/) (2021)
- [SketchXAI: A First Look at Explainability for Human Sketches](https://mlsanity.com/paper/2304.11744/) (2023)
- [SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation](https://mlsanity.com/paper/2308.14191/) (2023)
- [How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?](https://mlsanity.com/paper/2403.07203/) (2024)
- [FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations](https://mlsanity.com/paper/2411.10818/) (2024)
- [Sketch Video Synthesis](https://mlsanity.com/paper/2311.15306/) (2023)
- [What Sketch Explainability Really Means for Downstream Tasks](https://mlsanity.com/paper/2403.09480/) (2024)
- [Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching](https://mlsanity.com/paper/2602.12280/) (2026)
- [Calliar: An Online Handwritten Dataset for Arabic Calligraphy](https://mlsanity.com/paper/2106.10745/) (2021)
- [DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation](https://mlsanity.com/paper/2311.17786/) (2023)
- [Do Generalised Classifiers really work on Human Drawn Sketches?](https://mlsanity.com/paper/2407.03893/) (2024)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion](https://mlsanity.com/paper/2503.23752/) (2025)
- [VideoSketcher: Sequential Sketch Generation Using Video Model Priors](https://mlsanity.com/paper/2602.15819/) (2026)
- [Inkorrect: Online Handwriting Spelling Correction](https://mlsanity.com/paper/2202.13794/) (2022)
- [Conditional Human Sketch Synthesis with Explicit Abstraction Control](https://mlsanity.com/paper/2306.09274/) (2023)
- [SketchTriplet: Self-Supervised Scenarized Sketch-Text-Image Triplet Generation](https://mlsanity.com/paper/2405.18801/) (2024)
- [Sketch & Paint: Stroke-by-Stroke Evolution of Visual Artworks](https://mlsanity.com/paper/2502.20119/) (2025)

## Abstract (arXiv)

The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process. The landmark SketchRNN provided breakthrough by sequentially generating sketches as a sequence of waypoints. However this leads to low-resolution image generation, and failure to model long sketches. In this paper we present B'ezierSketch, a novel generative model for fully vector sketches that are automatically scalable and high-resolution. To this end, we first introduce a novel inverse graphics approach to stroke embedding that trains an encoder to embed each stroke to its best fit B'ezier curve. This enables us to treat sketches as short sequences of paramaterized strokes and thus train a recurrent sketch generator with greater capacity for longer sketches, while producing scalable high-resolution results. We report qualitative and quantitative results on the Quick, Draw! benchmark.