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

arXiv: https://arxiv.org/abs/2609.19911 · HTML: https://mlsanity.com/paper/2609.19911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 30)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark](https://mlsanity.com/paper/2306.06687/) (2023)
- [Multi-View Transformer for 3D Visual Grounding](https://mlsanity.com/paper/2204.02174/) (2022)
- [LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent](https://mlsanity.com/paper/2309.12311/) (2023)
- [SAT: 2D Semantics Assisted Training for 3D Visual Grounding](https://mlsanity.com/paper/2105.11450/) (2021)
- [RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data](https://mlsanity.com/paper/2210.12634/) (2022)
- [LanguageRefer: Spatial-Language Model for 3D Visual Grounding](https://mlsanity.com/paper/2107.03438/) (2021)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation](https://mlsanity.com/paper/2507.04047/) (2025)
- [MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors](https://mlsanity.com/paper/2405.01413/) (2024)
- [Generative Gaussian Splatting for Unbounded 3D City Generation](https://mlsanity.com/paper/2406.06526/) (2024)
- [Text2Pos: Text-to-Point-Cloud Cross-Modal Localization](https://mlsanity.com/paper/2203.15125/) (2022)
- [3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding](https://mlsanity.com/paper/2401.03201/) (2024)
- [Agent3D-Zero: An Agent for Zero-shot 3D Understanding](https://mlsanity.com/paper/2403.11835/) (2024)
- [A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions](https://mlsanity.com/paper/2406.05785/) (2024)
- [ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning](https://mlsanity.com/paper/2503.23297/) (2025)
- [3EED: Ground Everything Everywhere in 3D](https://mlsanity.com/paper/2511.01755/) (2025)
- [Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision](https://mlsanity.com/paper/2410.08209/) (2024)
- [SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence](https://mlsanity.com/paper/2505.12703/) (2025)
- [ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition](https://mlsanity.com/paper/2507.11261/) (2025)
- [View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs](https://mlsanity.com/paper/2512.09215/) (2025)
- [City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning](https://mlsanity.com/paper/2507.12795/) (2025)
- [3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding](https://mlsanity.com/paper/2603.23447/) (2026)

## Abstract (arXiv)

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.