SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916408569364480 |
|---|---|
| author | Janampa, Sebastian Pattichis, Marios |
| author_facet | Janampa, Sebastian Pattichis, Marios |
| contents | Camera calibration consists of estimating camera parameters such as the zenith vanishing point and horizon line. Estimating the camera parameters allows other tasks like 3D rendering, artificial reality effects, and object insertion in an image. Transformer-based models have provided promising results; however, they lack cross-scale interaction. In this work, we introduce \textit{multi-Scale defOrmable transFormer for camera calibratIon with enhanced line queries}, SOFI. SOFI improves the line queries used in CTRL-C and MSCC by using both line content and line geometric features. Moreover, SOFI's line queries allow transformer models to adopt the multi-scale deformable attention mechanism to promote cross-scale interaction between the feature maps produced by the backbone. SOFI outperforms existing methods on the \textit {Google Street View}, \textit {Horizon Line in the Wild}, and \textit {Holicity} datasets while keeping a competitive inference speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15553 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries Janampa, Sebastian Pattichis, Marios Computer Vision and Pattern Recognition Camera calibration consists of estimating camera parameters such as the zenith vanishing point and horizon line. Estimating the camera parameters allows other tasks like 3D rendering, artificial reality effects, and object insertion in an image. Transformer-based models have provided promising results; however, they lack cross-scale interaction. In this work, we introduce \textit{multi-Scale defOrmable transFormer for camera calibratIon with enhanced line queries}, SOFI. SOFI improves the line queries used in CTRL-C and MSCC by using both line content and line geometric features. Moreover, SOFI's line queries allow transformer models to adopt the multi-scale deformable attention mechanism to promote cross-scale interaction between the feature maps produced by the backbone. SOFI outperforms existing methods on the \textit {Google Street View}, \textit {Horizon Line in the Wild}, and \textit {Holicity} datasets while keeping a competitive inference speed. |
| title | SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.15553 |