Skip to yearly menu bar Skip to main content


Poster
in
Workshop: CODEML: Championing Open-source DEvelopment in Machine Learning

Spatial Reasoning over Continuous Variables with PySpaRe

Bartlomiej Pogodzinski · Christopher Wewer · Bernt Schiele · Jan Eric Lenssen

[ ] [ Project Page ]
Fri 18 Jul 2:15 p.m. PDT — 3 p.m. PDT

Abstract:

We present PySpaRe, a software framework to perform spatial reasoning over continuous variables with generative denoising models. Denoising generative models have become the de-facto standard for image generation, due to their effectiveness in sampling from complex, high-dimensional distributions. Recently, they have started being explored in the context of reasoning over multiple continuous variables. Providing infrastructure for generative reasoning with such models requires a high effort, due to a wide range of different denoising formulations, samplers, and inference strategies. Our presented framework aims to facilitate research in this area, providing easy-to-use interfaces to control variable mapping from arbitrary data domains, generative model paradigms, and inference strategies. The PySpaRe framework is openly available online.

Chat is not available.