Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2604.00597 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918423113498624 |
|---|---|
| author | Hashimoto, Hiroki Goto, Hiromichi Sugai, Hiroyuki Kera, Hiroshi Kawamoto, Kazuhiko |
| author_facet | Hashimoto, Hiroki Goto, Hiromichi Sugai, Hiroyuki Kera, Hiroshi Kawamoto, Kazuhiko |
| contents | Robust trajectory planning under camera viewpoint changes is important for scalable end-to-end autonomous driving. However, existing models often depend heavily on the camera viewpoints seen during training. We investigate an augmentation-free approach that leverages geometric priors from a 3D foundation model. The method injects per-pixel 3D positions derived from depth estimates as positional embeddings and fuses intermediate geometric features through cross-attention. Experiments on the VR-Drive camera viewpoint perturbation benchmark show reduced performance degradation under most perturbation conditions, with clear improvements under pitch and height perturbations. Gains under longitudinal translation are smaller, suggesting that more viewpoint-agnostic integration is needed for robustness to camera viewpoint changes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00597 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model Priors Hashimoto, Hiroki Goto, Hiromichi Sugai, Hiroyuki Kera, Hiroshi Kawamoto, Kazuhiko Computer Vision and Pattern Recognition Robust trajectory planning under camera viewpoint changes is important for scalable end-to-end autonomous driving. However, existing models often depend heavily on the camera viewpoints seen during training. We investigate an augmentation-free approach that leverages geometric priors from a 3D foundation model. The method injects per-pixel 3D positions derived from depth estimates as positional embeddings and fuses intermediate geometric features through cross-attention. Experiments on the VR-Drive camera viewpoint perturbation benchmark show reduced performance degradation under most perturbation conditions, with clear improvements under pitch and height perturbations. Gains under longitudinal translation are smaller, suggesting that more viewpoint-agnostic integration is needed for robustness to camera viewpoint changes. |
| title | Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.00597 |