nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Vision
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909351386546176 |
|---|---|
| author | Lichy, Daniel Su, Hang Badki, Abhishek Kautz, Jan Gallo, Orazio |
| author_facet | Lichy, Daniel Su, Hang Badki, Abhishek Kautz, Jan Gallo, Orazio |
| contents | We introduce nvTorchCam, an open-source library under the Apache 2.0 license, designed to make deep learning algorithms camera model-independent. nvTorchCam abstracts critical camera operations such as projection and unprojection, allowing developers to implement algorithms once and apply them across diverse camera models--including pinhole, fisheye, and 360 equirectangular panoramas, which are commonly used in automotive and real estate capture applications. Built on PyTorch, nvTorchCam is fully differentiable and supports GPU acceleration and batching for efficient computation. Furthermore, deep learning models trained for one camera type can be directly transferred to other camera types without requiring additional modification. In this paper, we provide an overview of nvTorchCam, its functionality, and present various code examples and diagrams to demonstrate its usage. Source code and installation instructions can be found on the nvTorchCam GitHub page at https://github.com/NVlabs/nvTorchCam. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12074 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Vision Lichy, Daniel Su, Hang Badki, Abhishek Kautz, Jan Gallo, Orazio Computer Vision and Pattern Recognition We introduce nvTorchCam, an open-source library under the Apache 2.0 license, designed to make deep learning algorithms camera model-independent. nvTorchCam abstracts critical camera operations such as projection and unprojection, allowing developers to implement algorithms once and apply them across diverse camera models--including pinhole, fisheye, and 360 equirectangular panoramas, which are commonly used in automotive and real estate capture applications. Built on PyTorch, nvTorchCam is fully differentiable and supports GPU acceleration and batching for efficient computation. Furthermore, deep learning models trained for one camera type can be directly transferred to other camera types without requiring additional modification. In this paper, we provide an overview of nvTorchCam, its functionality, and present various code examples and diagrams to demonstrate its usage. Source code and installation instructions can be found on the nvTorchCam GitHub page at https://github.com/NVlabs/nvTorchCam. |
| title | nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Vision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.12074 |