Acoustic Neural 3D Reconstruction Under Pose Drift
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911383321313280 |
|---|---|
| author | Lin, Tianxiang Qadri, Mohamad Zhang, Kevin Pediredla, Adithya Metzler, Christopher A. Kaess, Michael |
| author_facet | Lin, Tianxiang Qadri, Mohamad Zhang, Kevin Pediredla, Adithya Metzler, Christopher A. Kaess, Michael |
| contents | We consider the problem of optimizing neural implicit surfaces for 3D reconstruction using acoustic images collected with drifting sensor poses. The accuracy of current state-of-the-art 3D acoustic modeling algorithms is highly dependent on accurate pose estimation; small errors in sensor pose can lead to severe reconstruction artifacts. In this paper, we propose an algorithm that jointly optimizes the neural scene representation and sonar poses. Our algorithm does so by parameterizing the 6DoF poses as learnable parameters and backpropagating gradients through the neural renderer and implicit representation. We validated our algorithm on both real and simulated datasets. It produces high-fidelity 3D reconstructions even under significant pose drift. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08930 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Acoustic Neural 3D Reconstruction Under Pose Drift Lin, Tianxiang Qadri, Mohamad Zhang, Kevin Pediredla, Adithya Metzler, Christopher A. Kaess, Michael Signal Processing Computer Vision and Pattern Recognition Robotics We consider the problem of optimizing neural implicit surfaces for 3D reconstruction using acoustic images collected with drifting sensor poses. The accuracy of current state-of-the-art 3D acoustic modeling algorithms is highly dependent on accurate pose estimation; small errors in sensor pose can lead to severe reconstruction artifacts. In this paper, we propose an algorithm that jointly optimizes the neural scene representation and sonar poses. Our algorithm does so by parameterizing the 6DoF poses as learnable parameters and backpropagating gradients through the neural renderer and implicit representation. We validated our algorithm on both real and simulated datasets. It produces high-fidelity 3D reconstructions even under significant pose drift. |
| title | Acoustic Neural 3D Reconstruction Under Pose Drift |
| topic | Signal Processing Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2503.08930 |