Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models

TL;DR

This paper introduces SymPL, a symbolic framework that significantly improves vision-language models' ability to perform allocentric spatial reasoning by converting complex spatial questions into structured symbolic layouts.

Contribution

The paper presents SymPL, a novel symbolic projective layout method that enhances allocentric spatial reasoning in vision-language models, addressing a previously underexplored challenge.

Findings

Substantially improved allocentric and egocentric reasoning performance

Enhanced robustness under visual illusions and multi-view scenarios

Each component of SymPL contributes critically to performance gains

Abstract

Perspective-aware spatial reasoning involves understanding spatial relationships from specific viewpoints-either egocentric (observer-centered) or allocentric (object-centered). While vision-language models (VLMs) perform well in egocentric settings, their performance deteriorates when reasoning from allocentric viewpoints, where spatial relations must be inferred from the perspective of objects within the scene. In this study, we address this underexplored challenge by introducing Symbolic Projective Layout (SymPL), a framework that reformulates allocentric reasoning into symbolic-layout forms that VLMs inherently handle well. By leveraging four key factors-projection, abstraction, bipartition, and localization-SymPL converts allocentric questions into structured symbolic-layout representations. Extensive experiments demonstrate that this reformulation substantially improves performance in both allocentric and egocentric tasks, enhances robustness under visual illusions and multi-view scenarios, and that each component contributes critically to these gains. These results show that SymPL provides an effective and principled approach for addressing complex perspective-aware spatial reasoning.