2 papers
cs.CV2026
ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models
Qirui Shen, Wenda Wang, Jiachen Lu +5
Architectural spatial intelligence, the ability to recognize and infer architectural space, is fundamental to tasks such as robot navigation, embodied interaction, and 3D scene und…
cs.CV2026
Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches
Wenda Wang, Anqi Liu, Junqi Yang +4
Converting hand-drawn sketches into structured 3D geometries remains challenging due to the difficulty of representing non-Euclidean surfaces and maintaining topological consistenc…