Spatial Reasoners for Continuous Variables in Any Domain
Abstract
We present Spatial Reasoners, 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. Spatial Reasoners are openly available at https://spatialreasoners.github.io/
Cite
@article{arxiv.2507.10768,
title = {Spatial Reasoners for Continuous Variables in Any Domain},
author = {Bart Pogodzinski and Christopher Wewer and Bernt Schiele and Jan Eric Lenssen},
journal= {arXiv preprint arXiv:2507.10768},
year = {2025}
}
Comments
For the project documentation see https://spatialreasoners.github.io/ . The SRM project website is available at https://geometric-rl.mpi-inf.mpg.de/srm/ . The work was published on ICML 2025 CODEML workshop