NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913500926836736 |
|---|---|
| author | Feldmann, Casimir Siegenheim, Niall Hars, Nikolas Rabuzin, Lovro Ertugrul, Mert Wolfart, Luca Pollefeys, Marc Bauer, Zuria Oswald, Martin R. |
| author_facet | Feldmann, Casimir Siegenheim, Niall Hars, Nikolas Rabuzin, Lovro Ertugrul, Mert Wolfart, Luca Pollefeys, Marc Bauer, Zuria Oswald, Martin R. |
| contents | The capabilities of monocular depth estimation (MDE) models are limited by the availability of sufficient and diverse datasets. In the case of MDE models for autonomous driving, this issue is exacerbated by the linearity of the captured data trajectories. We propose a NeRF-based data augmentation pipeline to introduce synthetic data with more diverse viewing directions into training datasets and demonstrate the benefits of our approach to model performance and robustness. Our data augmentation pipeline, which we call \textit{NeRFmentation}, trains NeRFs on each scene in a dataset, filters out subpar NeRFs based on relevant metrics, and uses them to generate synthetic RGB-D images captured from new viewing directions. In this work, we apply our technique in conjunction with three state-of-the-art MDE architectures on the popular autonomous driving dataset, KITTI, augmenting its training set of the Eigen split. We evaluate the resulting performance gain on the original test set, a separate popular driving dataset, and our own synthetic test set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03771 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation Feldmann, Casimir Siegenheim, Niall Hars, Nikolas Rabuzin, Lovro Ertugrul, Mert Wolfart, Luca Pollefeys, Marc Bauer, Zuria Oswald, Martin R. Computer Vision and Pattern Recognition The capabilities of monocular depth estimation (MDE) models are limited by the availability of sufficient and diverse datasets. In the case of MDE models for autonomous driving, this issue is exacerbated by the linearity of the captured data trajectories. We propose a NeRF-based data augmentation pipeline to introduce synthetic data with more diverse viewing directions into training datasets and demonstrate the benefits of our approach to model performance and robustness. Our data augmentation pipeline, which we call \textit{NeRFmentation}, trains NeRFs on each scene in a dataset, filters out subpar NeRFs based on relevant metrics, and uses them to generate synthetic RGB-D images captured from new viewing directions. In this work, we apply our technique in conjunction with three state-of-the-art MDE architectures on the popular autonomous driving dataset, KITTI, augmenting its training set of the Eigen split. We evaluate the resulting performance gain on the original test set, a separate popular driving dataset, and our own synthetic test set. |
| title | NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.03771 |