Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps

2026-01-16

AI Summary

This work proposes Metric-CogMap and Cognitive Chain-of-Thought (Cog-CoT) to enhance spatial reasoning in 3D vision-language models by introducing the first interpretable, explicit 3D spatial reasoning mechanism. The approach integrates discrete grid-based and continuous metric space representations, enabling geometric reasoning through vector operations, bounding box distances, and occlusion-aware analysis. Remarkably, the model achieves 59.9% accuracy on VSI-Bench using only 50% of the labeled data—nearly matching the full-data baseline of 60.9%—and outperforms existing state-of-the-art methods by 5.3%, 4.8%, and 4.0% under 10%, 25%, and 50% training data regimes, respectively. These results demonstrate a significant reduction in reliance on supervised annotations while maintaining competitive performance.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

We propose Map2Thought, a framework that enables explicit and interpretable spatial reasoning for 3D VLMs. The framework is grounded in two key components: Metric Cognitive Map (Metric-CogMap) and Cognitive Chain-of-Thought (Cog-CoT). Metric-CogMap provides a unified spatial representation by integrating a discrete grid for relational reasoning with a continuous, metric-scale representation for precise geometric understanding. Building upon the Metric-CogMap, Cog-CoT performs explicit geometric reasoning through deterministic operations, including vector operations, bounding-box distances, and occlusion-aware appearance order cues, producing interpretable inference traces grounded in 3D structure. Experimental results show that Map2Thought enables explainable 3D understanding, achieving 59.9% accuracy using only half the supervision, closely matching the 60.9% baseline trained with the full dataset. It consistently outperforms state-of-the-art methods by 5.3%, 4.8%, and 4.0% under 10%, 25%, and 50% training subsets, respectively, on the VSI-Bench.

Problem

• 3D spatial reasoning
• visual language models
• cognitive maps
• interpretable reasoning
• metric representation

Innovation

• Metric Cognitive Map
• Cognitive Chain-of-Thought
• 3D spatial reasoning
• interpretable VLMs
• geometric reasoning