GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs

2026-09-03

AI Summary

GraFT通过3D场景图提供三维空间推理能力，无需训练即可提高多模态大语言模型的空间推理性能。

Abstract

3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unreliable in current multimodal large language models (MLLMs). These models falter at precise geometric measurement, at transforming between egocentric and allocentric viewpoints, and at grounding fine-grained appearance. The most common remedies fine-tune the model on large-scale curated spatial-reasoning datasets or attach dedicated encoders for 3D geometry, which typically couples the solution to costly supervision and a specific backbone. We instead introduce GraFT, a training-free framework that supplies the missing 3D structure through a compact, easily maintained 3D scene graph (3DSG). From this 3DSG, GraFT provides three spatial reasoning capabilities: (1) deterministic geometry through symbolic tools, (2) allocentric layout through a bird's-eye-view (BEV) rendering, and (3) visual-attribute grounding through task-relevant egocentric frames. On ScanQA, GraFT improves every metric over the same-backbone baseline, raising CIDEr by 27%. On VSI-Bench, GraFT improves frozen MLLMs by up to 65%, surpassing every proprietary and general-purpose open-source baseline, and several prominent fine-tuned spatial models.

Problem

• 3D spatial reasoning
• multimodal large language models
• geometric measurement
• viewpoint transformation
• visual-attribute grounding

Innovation

• Training-Free Framework
• 3D Scene Graph
• Spatial Reasoning
• Multimodal Large Language Models