GBlobs: Local LiDAR Geometry for Improved Sensor Placement Generalization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917029546557440 |
|---|---|
| author | Malić, Dušan Fruhwirth-Reisinger, Christian Prutsch, Alexander Lin, Wei Schulter, Samuel Possegger, Horst |
| author_facet | Malić, Dušan Fruhwirth-Reisinger, Christian Prutsch, Alexander Lin, Wei Schulter, Samuel Possegger, Horst |
| contents | This technical report outlines the top-ranking solution for RoboSense 2025: Track 3, achieving state-of-the-art performance on 3D object detection under various sensor placements. Our submission utilizes GBlobs, a local point cloud feature descriptor specifically designed to enhance model generalization across diverse LiDAR configurations. Current LiDAR-based 3D detectors often suffer from a \enquote{geometric shortcut} when trained on conventional global features (\ie, absolute Cartesian coordinates). This introduces a position bias that causes models to primarily rely on absolute object position rather than distinguishing shape and appearance characteristics. Although effective for in-domain data, this shortcut severely limits generalization when encountering different point distributions, such as those resulting from varying sensor placements. By using GBlobs as network input features, we effectively circumvent this geometric shortcut, compelling the network to learn robust, object-centric representations. This approach significantly enhances the model's ability to generalize, resulting in the exceptional performance demonstrated in this challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18539 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GBlobs: Local LiDAR Geometry for Improved Sensor Placement Generalization Malić, Dušan Fruhwirth-Reisinger, Christian Prutsch, Alexander Lin, Wei Schulter, Samuel Possegger, Horst Computer Vision and Pattern Recognition This technical report outlines the top-ranking solution for RoboSense 2025: Track 3, achieving state-of-the-art performance on 3D object detection under various sensor placements. Our submission utilizes GBlobs, a local point cloud feature descriptor specifically designed to enhance model generalization across diverse LiDAR configurations. Current LiDAR-based 3D detectors often suffer from a \enquote{geometric shortcut} when trained on conventional global features (\ie, absolute Cartesian coordinates). This introduces a position bias that causes models to primarily rely on absolute object position rather than distinguishing shape and appearance characteristics. Although effective for in-domain data, this shortcut severely limits generalization when encountering different point distributions, such as those resulting from varying sensor placements. By using GBlobs as network input features, we effectively circumvent this geometric shortcut, compelling the network to learn robust, object-centric representations. This approach significantly enhances the model's ability to generalize, resulting in the exceptional performance demonstrated in this challenge. |
| title | GBlobs: Local LiDAR Geometry for Improved Sensor Placement Generalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.18539 |