Abstract
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.
Abstract (translated)
连续性时间几何构造的生成建模，例如手写、 Sketch、绘图等，是通过自回归分布完成的。然而，这种严格排序的离散 factorization 未能捕捉到的图像数据的关键特性——由于单向可视化(因果性)，它无法构建整体理解，因此，时间数据被建模为固定采样率的离散 token 序列，而不是捕捉真正 underlying 概念。在本文中，我们介绍了一种强大的模型类别，名为“去噪扩散概率模型”(DDPM)，专门解决了图像数据的这些缺陷。我们的模型名为“ChiroDiff”，它不是自回归的，因此学习捕捉整体概念，因此可以很好地适应更高的时间采样率。此外，我们展示了许多重要的后续功能(例如条件采样、创造性混合)可以使用 ChiroDiff 灵活实现。我们还展示了一些独特的应用场景，例如随机向量化、去噪/修复、抽象等。我们对这些模型类别在相关数据集上进行定量和定性评估，并发现它更好或与竞争方法相当。
URL
https://arxiv.org/abs/2304.03785
