AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915359801475072 |
|---|---|
| author | Tirado-Garín, Javier Civera, Javier |
| author_facet | Tirado-Garín, Javier Civera, Javier |
| contents | We present AnyCalib, a method for calibrating the intrinsic parameters of a camera from a single in-the-wild image, that is agnostic to the camera model. Current methods are predominantly tailored to specific camera models and/or require extrinsic cues, such as the direction of gravity, to be visible in the image. In contrast, we argue that the perspective and distortion cues inherent in images are sufficient for model-agnostic camera calibration. To demonstrate this, we frame the calibration process as the regression of the rays corresponding to each pixel. We show, for the first time, that this intermediate representation allows for a closed-form recovery of the intrinsics for a wide range of camera models, including but not limited to: pinhole, Brown-Conrady and Kannala-Brandt. Our approach also applies to edited -- cropped and stretched -- images. Experimentally, we demonstrate that AnyCalib consistently outperforms alternative methods, including 3D foundation models, despite being trained on orders of magnitude less data. Code is available at https://github.com/javrtg/AnyCalib. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12701 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration Tirado-Garín, Javier Civera, Javier Computer Vision and Pattern Recognition We present AnyCalib, a method for calibrating the intrinsic parameters of a camera from a single in-the-wild image, that is agnostic to the camera model. Current methods are predominantly tailored to specific camera models and/or require extrinsic cues, such as the direction of gravity, to be visible in the image. In contrast, we argue that the perspective and distortion cues inherent in images are sufficient for model-agnostic camera calibration. To demonstrate this, we frame the calibration process as the regression of the rays corresponding to each pixel. We show, for the first time, that this intermediate representation allows for a closed-form recovery of the intrinsics for a wide range of camera models, including but not limited to: pinhole, Brown-Conrady and Kannala-Brandt. Our approach also applies to edited -- cropped and stretched -- images. Experimentally, we demonstrate that AnyCalib consistently outperforms alternative methods, including 3D foundation models, despite being trained on orders of magnitude less data. Code is available at https://github.com/javrtg/AnyCalib. |
| title | AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12701 |