← Back to all news
arXiv Computer Vision By Shuai Zhang, Hongye Hou, Qinghe Liu, Zhuoxiao Li, Dongli Wu, Jing Ou, Yuan Liu, Wufan Zhao

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

Read the original on arXiv Computer Vision →

CitySTAR introduces a training‑free framework that transforms billion‑scale urban point clouds into a query‑ready scene graph of open‑vocabulary 3D instances, using CodeLLM‑driven tools to supply multimodal evidence for node attributes and spatial relations. It models target‑context topology with paired hypergraphs and performs bidirectional topology verification for structural disambiguation, followed by a Reflective Cross‑modal Grounding module that integrates topology consistency and 2D visual evidence to decide over a metric‑aware 3D context graph. The authors also present CitySTAR‑3D, a benchmark that enhances semantic coverage, instance completeness, bounding‑box fidelity, and spatial‑relation complexity for city‑scale 3D grounding, and report extensive experiments showing consistent improvements in open‑world urban 3D grounding with strong interpretability and generalization.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
6d ago

3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement

3D-SceneQ is a new 3D large language model that tackles two key limitations of existing 3D scene understanding pipelines: the inclusion of irrelevant object tokens that add noise, and the exclusive use of point cloud data that lacks rich semantic cues. It introduces a Query‑Guided Adaptive Pruning (QGAP) module that selectively keeps task‑relevant objects based on user instructions, and a Multi‑modal Object‑level Feature Enhancement (MOFE) module that fuses 2D feature embeddings into the 3D representation to enrich semantic information. Experiments show that 3D‑SceneQ surpasses state‑of‑the‑art methods on several benchmarks, achieving significant gains in metrics such as CIDEr and EM@1.

By Yongqi Shan, Lu Zhang, Jiazuo Yu, Yunzhi Zhuge, Huchuan Lu
llmsragefficiencymultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
Oct 21

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

HERMES++ is a unified driving world model that simultaneously performs 3D scene understanding and future geometry prediction. It uses a BEV representation to merge multi‑view spatial data for LLM compatibility, introduces LLM‑enhanced world queries for knowledge transfer, and employs a Current‑to‑Future Link to condition future geometry on semantic context. A Joint Geometric Optimization strategy enforces structural integrity by combining explicit geometric constraints with implicit latent regularization, and extensive benchmark tests show that HERMES++ outperforms specialist methods in both point cloud prediction and scene understanding.

By Xin Zhou, Dingkang Liang, Xiwu Chen, Feiyang Tan, Dingyuan Zhang, Hengshuang Zhao, Xiang Bai
llmsagentsroboticsbenchmarks
More like this →
arXiv Computer Vision
Sep 28

GraphWrit3R: End-to-End 3D Scene Graph Writing

arXiv:2609.31595v1 Announce Type: new Abstract: 3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and functio...

By Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar, Sebastian Koch, Iro Armeni, Luc Van Gool, Danda Pani Paudel
llmsbenchmarkssafety
More like this →
arXiv AI
Sep 4

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

GraFT is a training‑free framework that enhances spatial reasoning in multimodal large language models by integrating a compact 3D scene graph (3DSG). It offers deterministic geometry via symbolic tools, allocentric layout through bird’s‑eye‑view rendering, and visual‑attribute grounding using egocentric frames. Experiments on ScanQA and VSI‑Bench show significant performance gains, with CIDEr increasing by 27% and improvements up to 65% over baseline models.

By Junqing Du, Fernando Ropero, Erkin Turkoz, Yanfeng Zhang, Lu Liu
llmsfine-tuningmultimodal
More like this →