ChiroDiff: Modelling chirographic data with Diffusion Models

International Conference on Learning Representations (ICLR), 2023
Generative Models

Ayan Das

SketchX, CVSSP, University of Surrey

Yongxin Yang

Queen Mary University of London, UK

Timothy Hospedales

University of Edinburgh, UK

Samsung AI Center, Cambridge

Tao Xiang

SketchX, CVSSP, University of Surrey

Yi-Zhe Song

SketchX, CVSSP, University of Surrey


January 21, 2023

Paper (official) Paper (arXiv) Code


Generative modelling over continuous-time geometric constructs, a.k.a chirographic data 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.


BibTeX citation:
  author = {Das, Ayan and Yang, Yongxin and Hospedales, Timothy and
    Xiang, Tao and Song, Yi-Zhe},
  title = {ChiroDiff: {Modelling} Chirographic Data with {Diffusion}
  booktitle = {International Conference on Learning Representations
    (ICLR), 2023},
  date = {2023-01-21},
  url = {},
  langid = {en}
For attribution, please cite this work as:
Das, Ayan, Yongxin Yang, Timothy Hospedales, Tao Xiang, and Yi-Zhe Song. 2023. “ChiroDiff: Modelling Chirographic Data with Diffusion Models.” In International Conference on Learning Representations (ICLR), 2023.