SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning
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_ | 1866911952652992512 |
|---|---|
| author | Zhang, Runmin Ma, Jun Cao, Si-Yuan Luo, Lun Yu, Beinan Chen, Shu-Jie Li, Junwei Shen, Hui-Liang |
| author_facet | Zhang, Runmin Ma, Jun Cao, Si-Yuan Luo, Lun Yu, Beinan Chen, Shu-Jie Li, Junwei Shen, Hui-Liang |
| contents | We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal self-supervised learning is first presented to facilitate the unsupervised cross-modal homography estimation. The correlation-based homography estimation network and the consistent feature map projection are combined to form the learnable architecture of SCPNet, boosting the unsupervised learning framework. SCPNet is the first to achieve effective unsupervised homography estimation on the satellite-map image pair cross-modal dataset, GoogleMap, under [-32,+32] offset on a 128x128 image, leading the supervised approach MHN by 14.0% of mean average corner error (MACE). We further conduct extensive experiments on several cross-modal/spectral and manually-made inconsistent datasets, on which SCPNet achieves the state-of-the-art (SOTA) performance among unsupervised approaches, and owns 49.0%, 25.2%, 36.4%, and 10.7% lower MACEs than the supervised approach MHN. Source code is available at https://github.com/RM-Zhang/SCPNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08148 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning Zhang, Runmin Ma, Jun Cao, Si-Yuan Luo, Lun Yu, Beinan Chen, Shu-Jie Li, Junwei Shen, Hui-Liang Computer Vision and Pattern Recognition We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal self-supervised learning is first presented to facilitate the unsupervised cross-modal homography estimation. The correlation-based homography estimation network and the consistent feature map projection are combined to form the learnable architecture of SCPNet, boosting the unsupervised learning framework. SCPNet is the first to achieve effective unsupervised homography estimation on the satellite-map image pair cross-modal dataset, GoogleMap, under [-32,+32] offset on a 128x128 image, leading the supervised approach MHN by 14.0% of mean average corner error (MACE). We further conduct extensive experiments on several cross-modal/spectral and manually-made inconsistent datasets, on which SCPNet achieves the state-of-the-art (SOTA) performance among unsupervised approaches, and owns 49.0%, 25.2%, 36.4%, and 10.7% lower MACEs than the supervised approach MHN. Source code is available at https://github.com/RM-Zhang/SCPNet. |
| title | SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.08148 |