AI RESEARCH
Query-Calibrated Segmental Admission for Descriptor-Agnostic LiDAR Loop Closure in Repetitive Environments
arXiv CS.CV
•
ArXi:2512.09447v2 Announce Type: replace-cross Structurally repetitive environments produce visually plausible but aliased LiDAR loop candidates that can destabilize pose-graph optimization when admitted as loop factors. We propose Query-Calibrated Segmental Admission (QCSA), a descriptor-agnostic sparse loop-admission policy for graph-stability-oriented insertion. The policy scores short descriptor segments against hard negatives, calibrates which query-level segment hypotheses reach geometry, and inserts representative pairs validated by Generalized Iterative Closest Point (G.