ChiroDiff: Modelling chirographic data with Diffusion Models

Ayan Das, Yongxin Yang, Timothy M Hospedales, Tao Xiang, Yi-Zhe Song

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationThe Eleventh International Conference on Learning Representations
Subtitle of host publicationICLR 2023
Number of pages15
Publication statusPublished - 1 May 2023
EventThe Eleventh International Conference on Learning Representations - Kigali, Rwanda
Duration: 1 May 20235 May 2023


ConferenceThe Eleventh International Conference on Learning Representations
Abbreviated titleICLR 2023
Internet address


Dive into the research topics of 'ChiroDiff: Modelling chirographic data with Diffusion Models'. Together they form a unique fingerprint.

Cite this