AI RESEARCH
OREN: Octree Residual Network for Real-Time Euclidean Signed Distance Mapping
arXiv CS.AI
•
ArXi:2510.18999v2 Announce Type: replace-cross Reconstructing signed distance functions (SDFs) from point cloud data benefits many robot autonomy capabilities, including localization, mapping, motion planning, and control. Methods that online and large-scale SDF reconstruction often rely on discrete volumetric data structures, which affects the continuity and differentiability of the SDF estimates.