3 papers
cs.CV2026
WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory
Chong Liu, Luxuan Fu, Xuyu Feng +2
The paradigm of digital twin cities is shifting from coarse visual mapping toward more precise and actionable digitization of urban assets. However, existing datasets predominantly…
cs.CV2026
Unleashing the Capabilities of Large Vision-Language Models for Intelligent Perception of Roadside Infrastructure
Luxuan Fu, Chong Liu, Bisheng Yang +1
Automated perception of urban roadside infrastructure is crucial for smart city management, yet general-purpose models often struggle to capture the necessary fine-grained attribut…
cs.CV2026
SVII-3D: Advancing Roadside Infrastructure Inventory with Decimeter-level 3D Localization and Comprehension from Sparse Street Imagery
Chong Liu, Luxuan Fu, Yang Jia +2
The automated creation of digital twins and precise asset inventories is a critical task in smart city construction and facility lifecycle management. However, utilizing cost-effec…