Urban Scene Understanding

CitySTAR: Agent-Driven Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding featured image

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

NeurIPS 2026 · First author. CitySTAR grounds natural-language queries in city-scale 3D scenes through structured constraints, scene graphs and topology-aware reasoning.

shuai-zhang
•
UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Shared–Private Multimodal Decomposition featured image

UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Shared–Private Multimodal Decomposition

CVPR 2026 Findings · First author. UniD-Shift separates shared and modality-specific features for interpretable 2D–3D semantic segmentation and cross-domain generalization.

shuai-zhang
•