Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models
This addresses the underexplored challenge of allocentric spatial reasoning for vision-language models, with incremental improvements in a specific domain.
The paper tackled the problem of allocentric spatial reasoning in vision-language models, which perform poorly compared to egocentric reasoning, by introducing the Symbolic Projective Layout (SymPL) framework that reformulates allocentric questions into symbolic-layout forms, resulting in substantial performance improvements in both allocentric and egocentric tasks and enhanced robustness under visual illusions and multi-view scenarios.
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.