PROBE is a learning-free LiDAR place recognition descriptor using probabilistic Bernoulli occupancy in BEV with analytical translation marginalization via polar Jacobian, achieving top handcrafted accuracy on multi-session tasks across four datasets.
Scan context++: Structural place recog- nition robust to rotation and lateral variations in urban environments,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
COMPASS builds matching multi-channel descriptors from floor-plan priors and fisheye images to enable cross-modal structural localization.
citing papers explorer
-
PROBE: Probabilistic Occupancy BEV Encoding with Analytical Translation Robustness for 3D Place Recognition
PROBE is a learning-free LiDAR place recognition descriptor using probabilistic Bernoulli occupancy in BEV with analytical translation marginalization via polar Jacobian, achieving top handcrafted accuracy on multi-session tasks across four datasets.
-
COMPASS: COmpact Multi-channel Prior-map And Scene Signature for Floor-Plan-Based Visual Localization
COMPASS builds matching multi-channel descriptors from floor-plan priors and fisheye images to enable cross-modal structural localization.