Raymoval: Raycasting-based Dynamic Object Removal for Static 3D Mapping
About
Static mapping is fundamental to robot navigation, providing a persistent geometric prior and a consistent reference for long-term autonomy. However, dynamic objects leave residual traces and cause surface loss, which reduces map consistency. We propose a raycasting-based module for dynamic object removal in static 3D mapping. Each scan is projected onto an azimuth-elevation grid, and for every viewing direction we compare the bin-wise minimum range with the map's first-hit distance computed by raycasting. Furthermore, we apply a raycast consistency test that separates dynamic from static points. Finally, a spatial consistency validation step refines labels, producing static maps with lower residual dynamics and reduced over-removal. We evaluate our approach quantitatively and qualitatively on SemanticKITTI and a challenging custom dataset, and show consistent static mapping results.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Dynamic Object Removal | SemanticKITTI (Sequence 07) | -- | 7 | |
| Dynamic Object Removal | SemanticKITTI (Sequence 00) | PR94.046 | 5 | |
| Dynamic Object Removal | SemanticKITTI (Sequence 02) | PR (%)95.144 | 5 | |
| Dynamic Object Removal | SemanticKITTI (Sequence 05) | Precision (PR)93.394 | 5 | |
| Dynamic Object Removal | SemanticKITTI | Precision (%)93.217 | 5 | |
| Dynamic Object Removal | SemanticKITTI (Sequence 01) | PR91.854 | 5 |