2 papers
cs.CV2026
SR-Nav: Spatial Relationships Matter for Zero-shot Object Goal Navigation
Leyuan Fang, Zan Mao, Zijing Wang +1
Zero-shot object-goal navigation aims to find target objects in unseen environments using only egocentric observation. Recent methods leverage foundation models' comprehension and…
cs.CV2025
UniVector: Unified Vector Extraction via Instance-Geometry Interaction
Yinglong Yan, Jun Yue, Shaobo Xia +7
Vector extraction retrieves structured vector geometry from raster images, offering high-fidelity representation and broad applicability. Existing methods, however, are usually tai…