The City that Never Settles: Simulation-based LiDAR Dataset for Long-Term Place Recognition Under Extreme Structural Changes

TL;DR

This paper introduces the CNS dataset, a large-scale simulation-based collection capturing extensive structural changes in urban environments to evaluate and improve long-term LiDAR-based place recognition methods.

Contribution

The paper presents the CNS dataset created with CARLA simulator, including a symmetric structural change metric TCR_sym, and evaluates current PR methods under extreme environmental transformations.

Findings

CNS dataset captures more extensive changes than existing benchmarks.

State-of-the-art LiDAR-based PR methods show significant performance drops on CNS.

The dataset highlights the need for more robust place recognition algorithms.

Abstract

Large-scale construction and demolition significantly challenge long-term place recognition (PR) by drastically reshaping urban and suburban environments. Existing datasets predominantly reflect limited or indoor-focused changes, failing to adequately represent extensive outdoor transformations. To bridge this gap, we introduce the City that Never Settles (CNS) dataset, a simulation-based dataset created using the CARLA simulator, capturing major structural changes-such as building construction and demolition-across diverse maps and sequences. Additionally, we propose TCR_sym, a symmetric version of the original TCR metric, enabling consistent measurement of structural changes irrespective of source-target ordering. Quantitative comparisons demonstrate that CNS encompasses more extensive transformations than current real-world benchmarks. Evaluations of state-of-the-art LiDAR-based PR methods on CNS reveal substantial performance degradation, underscoring the need for robust algorithms capable of handling significant environmental changes. Our dataset is available at https://github.com/Hyunho111/CNS_dataset.