SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding
Abstract
SATURN uses approximate 3D scene reconstruction, soft perspective-aware predicates, and a training-free symbolic executor to improve compositional spatial reasoning under increasing depth and viewpoint complexity, as evaluated on 3D FORCE and MindCube.
Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existing tool-augmented spatial reasoning methods make reasoning more explicit, but often rely on low-level geometric procedures and hard binary decisions over noisy perception. We propose SATURN, a neuro-symbolic framework for perspective-aware compositional spatial reasoning. SATURN reconstructs an approximate 3D scene, derives soft perspective-aware spatial predicates, and composes them with a training-free Pythonic symbolic executor, separating perception from reasoning while preserving uncertainty through multi-hop inference. We also introduce 3D FORCE, a diagnostic benchmark that controls reasoning depth, view, and perspective composition for spatial arrangement grounding (SAG) and referring expression grounding (REF). On 3D FORCE, VLMs and spatially trained models degrade sharply as depth and perspective complexity increase, whereas SATURN degrades the least and outperforms every baseline at each depth. On the real-world MindCube benchmark, SATURN achieves \(78.06\%\) overall accuracy, outperforming the strongest baseline by \(14\) percentage points.
Get this paper in your agent:
hf papers read 2606.22694 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 3
remyxai/SpaceQwen2.5-VL-3B-Instruct
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 2
Collections including this paper 0
No Collection including this paper