# ChiroDiff: Modelling chirographic data with Diffusion Models

arXiv: https://arxiv.org/abs/2304.03785 · HTML: https://mlsanity.com/paper/2304.03785/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 7 Apr 2023.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Equivariant Diffusion for Molecule Generation in 3D](https://mlsanity.com/paper/2203.17003/) (2022)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation](https://mlsanity.com/paper/2203.02923/) (2022)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Learning Gradient Fields for Shape Generation](https://mlsanity.com/paper/2008.06520/) (2020)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)

## Built on by (most cited first, 14 of 14)

- [VecFusion: Vector Font Generation with Diffusion](https://mlsanity.com/paper/2312.10540/) (2023)
- [SketchINR: A First Look into Sketches as Implicit Neural Representations](https://mlsanity.com/paper/2403.09344/) (2024)
- [Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation](https://mlsanity.com/paper/2508.03256/) (2025)
- [DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance](https://mlsanity.com/paper/2512.10894/) (2025)
- [Decoupling Layout from Glyph in Online Chinese Handwriting Generation](https://mlsanity.com/paper/2410.02309/) (2024)
- [Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss](https://mlsanity.com/paper/2403.16728/) (2024)
- [CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion](https://mlsanity.com/paper/2404.00412/) (2024)
- [StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion](https://mlsanity.com/paper/2503.23752/) (2025)
- [Generating Sketches in a Hierarchical Auto-Regressive Process for Flexible Sketch Drawing Manipulation at Stroke-Level](https://mlsanity.com/paper/2511.07889/) (2025)
- [Sparse-to-Sparse Training of Diffusion Models](https://mlsanity.com/paper/2504.21380/) (2025)
- [Teaching an Agent to Sketch One Part at a Time](https://mlsanity.com/paper/2603.19500/) (2026)
- [Text to Sketch Generation with Multi-Styles](https://mlsanity.com/paper/2511.04123/) (2025)
- [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)

Generative modelling over continuous-time geometric constructs, a.k.a such as handwriting, sketches, drawings etc., have been accomplished through autoregressive distributions. Such strictly-ordered discrete factorization however falls short of capturing key properties of chirographic data -- it fails to build holistic understanding of the temporal concept due to one-way visibility (causality). Consequently, temporal data has been modelled as discrete token sequences of fixed sampling rate instead of capturing the true underlying concept. In this paper, we introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data that specifically addresses these flaws. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate up to a good extent. Moreover, we show that many important downstream utilities (e.g. conditional sampling, creative mixing) can be flexibly implemented using ChiroDiff. We further show some unique use-cases like stochastic vectorization, de-noising/healing, abstraction are also possible with this model-class. We perform quantitative and qualitative evaluation of our framework on relevant datasets and found it to be better or on par with competing approaches.