{"ID":23475131,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19911","arxiv_id":"2609.19911","title":"CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding","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.","short_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 sem...","url_abs":"https://arxiv.org/abs/2609.19911","url_pdf":"https://arxiv.org/pdf/2609.19911v1","authors":"[\"Shuai Zhang\",\"Hongye Hou\",\"Qinghe Liu\",\"Zhuoxiao Li\",\"Dongli Wu\",\"Jing Ou\",\"Yuan Liu\",\"Wufan Zhao\"]","published":"2026-09-17T08:53:13Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false}