# CoSE: Compositional Stroke Embeddings

arXiv: https://arxiv.org/abs/2006.09930 · HTML: https://mlsanity.com/paper/2006.09930/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 26 of 26)

- [SketchGen: Generating Constrained CAD Sketches](https://mlsanity.com/paper/2106.02711/) (2021)
- [ProcessPainter: Learn Painting Process from Sequence Data](https://mlsanity.com/paper/2406.06062/) (2024)
- [Disentangling Writer and Character Styles for Handwriting Generation](https://mlsanity.com/paper/2303.14736/) (2023)
- [Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval](https://mlsanity.com/paper/2203.14817/) (2022)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [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)
- [Recognizing Vector Graphics without Rasterization](https://mlsanity.com/paper/2111.03281/) (2021)
- [Decoupling Layout from Glyph in Online Chinese Handwriting Generation](https://mlsanity.com/paper/2410.02309/) (2024)
- [Drawing out of Distribution with Neuro-Symbolic Generative Models](https://mlsanity.com/paper/2206.01829/) (2022)
- [SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition](https://mlsanity.com/paper/2405.03099/) (2024)
- [Sketch-based Creativity Support Tools using Deep Learning](https://mlsanity.com/paper/2111.09991/) (2021)
- [Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching](https://mlsanity.com/paper/2602.12280/) (2026)
- [RendNet: Unified 2D/3D Recognizer With Latent Space Rendering](https://mlsanity.com/paper/2206.10066/) (2022)
- [NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation](https://mlsanity.com/paper/2106.13435/) (2021)
- [Multi-granularity Association Learning Framework for on-the-fly Fine-Grained Sketch-based Image Retrieval](https://mlsanity.com/paper/2201.05007/) (2022)
- [Inkorrect: Online Handwriting Spelling Correction](https://mlsanity.com/paper/2202.13794/) (2022)
- [Visual Intelligence through Human Interaction](https://mlsanity.com/paper/2111.06913/) (2021)
- [Character Generation through Self-Supervised Vectorization](https://mlsanity.com/paper/2208.02012/) (2022)
- [Sampling and Ranking for Digital Ink Generation on a tight computational budget](https://mlsanity.com/paper/2306.03103/) (2023)
- [Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors](https://mlsanity.com/paper/2601.05508/) (2026)
- [SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion](https://mlsanity.com/paper/2607.23580/) (2026)
- [Bridging Online and Offline Handwriting via Differentiable Physical Rendering](https://mlsanity.com/paper/2608.03198/) (2026)
- [Draw This First](https://mlsanity.com/paper/2608.12064/) (2026)
- [SketchFlow: Zero-Shot Vector Sketch Generation via GMM Prior Flow in CLIP Latent Space](https://mlsanity.com/paper/2608.21659/) (2026)

## Abstract (arXiv)

We present a generative model for complex free-form structures such as stroke-based drawing tasks. While previous approaches rely on sequence-based models for drawings of basic objects or handwritten text, we propose a model that treats drawings as a collection of strokes that can be composed into complex structures such as diagrams (e.g., flow-charts). At the core of the approach lies a novel autoencoder that projects variable-length strokes into a latent space of fixed dimension. This representation space allows a relational model, operating in latent space, to better capture the relationship between strokes and to predict subsequent strokes. We demonstrate qualitatively and quantitatively that our proposed approach is able to model the appearance of individual strokes, as well as the compositional structure of larger diagram drawings. Our approach is suitable for interactive use cases such as auto-completing diagrams. We make code and models publicly available at https://eth-ait.github.io/cose.