PROBE: Probabilistic Occupancy BEV Encoding with Analytical Translation Robustness for 3D Place Recognition

TL;DR

PROBE is a learning-free LiDAR place recognition method that models occupancy probabilistically, analytically marginalizes translation uncertainty, and achieves high accuracy across diverse datasets.

Contribution

PROBE introduces a novel probabilistic occupancy encoding with analytical translation robustness, improving cross-sensor generalization and reducing dataset tuning.

Findings

Achieves highest accuracy among handcrafted descriptors in multi-session evaluation.

Performs competitively with supervised baselines in single-session tests.

Demonstrates robustness across four diverse LiDAR datasets.

Abstract

We present PROBE (PRobabilistic Occupancy BEV Encoding), a learning-free LiDAR place recognition descriptor that models each BEV cell's occupancy as a Bernoulli random variable. Rather than relying on discrete point-cloud perturbations, PROBE analytically marginalizes over continuous Cartesian translations via the polar Jacobian, yielding a distance-adaptive angular uncertainty $\sigma_\theta = \sigma_t / r$ in $\mathcal{O}(R{\cdot}S)$ time. The primary parameter $\sigma_t$ represents the expected translational uncertainty in meters, a sensor-independent physical quantity that enhances cross-sensor generalization while reducing the need for extensive per-dataset tuning. Pairwise similarity combines a Bernoulli-KL Jaccard with exponential uncertainty gating and FFT-based height cosine similarity for rotation alignment. Evaluated on four datasets spanning four diverse LiDAR types, PROBE achieves the highest accuracy among handcrafted descriptors in multi-session evaluation and competitive single-session performance relative to both handcrafted and supervised baselines. The source code and supplementary materials are available at https://sites.google.com/view/probe-pr.