Showing 2026Show all
2 papers · 1 filter
cs.CV2026
PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models
Zhiang Chen, Nahyuk Lee, Boyang Sun +4
Registering two captures of the same indoor space taken at different times underpins persistent spatial memory for robots and AR systems, yet the realistic version of this task is…
cs.CV2026
TORA: Topological Representation Alignment for 3D Shape Assembly
Nahyuk Lee, Zhiang Chen, Marc Pollefeys +1
Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which…