CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding

2026-09-17

AI Summary

本文提出CitySTAR框架，通过结构化约束推理解决城市规模3D定位问题，利用场景图和拓扑验证提高自然语言与3D实体间匹配的准确性和可解释性。

Abstract

3D grounding aims to localize target entities in complex scenes from natural language and plays a fundamental role in embodied perception and spatial reasoning. However, existing approaches mostly rely on feature similarity or direct matching, making it difficult to connect natural-language intent with the implicit semantic and geometric structures hidden in billion-scale urban point clouds. We reformulate city-scale 3D grounding as structured constraint reasoning, where description semantics are organized into computable cross-modal constraints over open-vocabulary 3D entities, attributes, and spatial relations. We present CitySTAR, a training-free framework for reasoning-driven urban 3D grounding. CitySTAR lifts raw billion-scale urban point clouds into a query-ready scene graph of open-vocabulary 3D instances, with CodeLLM-driven tools supplying multimodal evidence for node attributes and 3D spatial relations. It then models target-context topology with paired hypergraphs and performs bidirectional topology verification for structural disambiguation. Finally, a Reflective Cross-modal Grounding module integrates topology consistency and candidate-centered 2D visual evidence to make decisions over a metric-aware 3D context graph. To further support this setting, we introduce CitySTAR-3D, an enhanced benchmark that improves semantic coverage, instance completeness, bounding-box fidelity, and spatial-relation complexity in city-scale 3D grounding. Extensive experiments show that CitySTAR consistently improves open-world urban 3D grounding while maintaining strong interpretability and generalization.

Problem

• 3D grounding
• natural language
• urban point clouds
• semantic and geometric structures
• structured constraint reasoning

Innovation

• structured constraint reasoning
• open-vocabulary 3D entities
• bidirectional topology verification
• reflective cross-modal grounding