Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2503.11199 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912274456772608 |
|---|---|
| author | Cui, Li Ding, Yang Hartley, Richard Xie, Zirui Kneip, Laurent Yu, Zhenghua |
| author_facet | Cui, Li Ding, Yang Hartley, Richard Xie, Zirui Kneip, Laurent Yu, Zhenghua |
| contents | We propose a novel, vision-only object-level SLAM framework for automotive applications representing 3D shapes by implicit signed distance functions. Our key innovation consists of augmenting the standard neural representation by a normalizing flow network. As a result, achieving strong representation power on the specific class of road vehicles is made possible by compact networks with only 16-dimensional latent codes. Furthermore, the newly proposed architecture exhibits a significant performance improvement in the presence of only sparse and noisy data, which is demonstrated through comparative experiments on synthetic data. The module is embedded into the back-end of a stereo-vision based framework for joint, incremental shape optimization. The loss function is given by a combination of a sparse 3D point-based SDF loss, a sparse rendering loss, and a semantic mask-based silhouette-consistency term. We furthermore leverage semantic information to determine keypoint extraction density in the front-end. Finally, experimental results on real-world data reveal accurate and reliable performance comparable to alternative frameworks that make use of direct depth readings. The proposed method performs well with only sparse 3D points obtained from bundle adjustment, and eventually continues to deliver stable results even under exclusive use of the mask-consistency term. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NF-SLAM: Effective, Normalizing Flow-supported Neural Field representations for object-level visual SLAM in automotive applications Cui, Li Ding, Yang Hartley, Richard Xie, Zirui Kneip, Laurent Yu, Zhenghua Computer Vision and Pattern Recognition We propose a novel, vision-only object-level SLAM framework for automotive applications representing 3D shapes by implicit signed distance functions. Our key innovation consists of augmenting the standard neural representation by a normalizing flow network. As a result, achieving strong representation power on the specific class of road vehicles is made possible by compact networks with only 16-dimensional latent codes. Furthermore, the newly proposed architecture exhibits a significant performance improvement in the presence of only sparse and noisy data, which is demonstrated through comparative experiments on synthetic data. The module is embedded into the back-end of a stereo-vision based framework for joint, incremental shape optimization. The loss function is given by a combination of a sparse 3D point-based SDF loss, a sparse rendering loss, and a semantic mask-based silhouette-consistency term. We furthermore leverage semantic information to determine keypoint extraction density in the front-end. Finally, experimental results on real-world data reveal accurate and reliable performance comparable to alternative frameworks that make use of direct depth readings. The proposed method performs well with only sparse 3D points obtained from bundle adjustment, and eventually continues to deliver stable results even under exclusive use of the mask-consistency term. |
| title | NF-SLAM: Effective, Normalizing Flow-supported Neural Field representations for object-level visual SLAM in automotive applications |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.11199 |