Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields

About

Neural distance fields offer a compact and continuous representation of 3D geometry, making them attractive for incremental LiDAR mapping. However, their online optimization is vulnerable to catastrophic forgetting, where new observations can degrade previously reconstructed geometry. Replay-based training is commonly used to address this issue, but existing methods typically rely on passive replay buffers and uniform sampling, which can waste memory on redundant observations and under-train poorly constrained regions. We propose LAPS, a replay management framework for incremental neural mapping that improves both replay retention and replay allocation during online updates. LAPS combines reliability-based active pooling to retain reliable historical samples under limited memory with uncertainty-guided active sampling to focus optimization on under-constrained regions. Experiments on synthetic and real-world benchmarks show that LAPS consistently improves reconstruction completeness while maintaining competitive geometric accuracy. On Oxford Spires, it improves recall by 4.66 pp and F1-score by 3.79 pp over PIN-SLAM on the Blenheim Palace 05 sequence. We release our open source implementation at: https://github.com/dongjae0107/LAPS.

Dongjae Lee, Wooseong Yang, Yifu Tao, Maurice Fallon, Ayoung Kim• 2026

Related benchmarks

TaskDatasetResultRank
3D ReconstructionOxford Spires (Keble College 04)
Accuracy11.23
6
Surface ReconstructionMaiCity
Accuracy3.62
6
3D ReconstructionOxford Spires (Blenheim Palace 05)
Accuracy8.89
6
3D ReconstructionOxford Spires (Christ Church 02)
Accuracy9.75
6
3D ReconstructionOxford Spires (Observatory Quarter 01)
Accuracy9.09
6
Surface ReconstructionNewer College 23
Accuracy6.55
6
Incremental LiDAR MappingMaiCity
Time (s)0.13
4
Incremental LiDAR MappingNewer College
Processing Time0.1
4
Showing 8 of 8 rows

Other info

Follow for update