Consensus Learning with Deep Sets for Essential Matrix Estimation
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_ | 1866915002288439296 |
|---|---|
| author | Moran, Dror Margalit, Yuval Trostianetsky, Guy Khatib, Fadi Galun, Meirav Basri, Ronen |
| author_facet | Moran, Dror Margalit, Yuval Trostianetsky, Guy Khatib, Fadi Galun, Meirav Basri, Ronen |
| contents | Robust estimation of the essential matrix, which encodes the relative position and orientation of two cameras, is a fundamental step in structure from motion pipelines. Recent deep-based methods achieved accurate estimation by using complex network architectures that involve graphs, attention layers, and hard pruning steps. Here, we propose a simpler network architecture based on Deep Sets. Given a collection of point matches extracted from two images, our method identifies outlier point matches and models the displacement noise in inlier matches. A weighted DLT module uses these predictions to regress the essential matrix. Our network achieves accurate recovery that is superior to existing networks with significantly more complex architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17414 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Consensus Learning with Deep Sets for Essential Matrix Estimation Moran, Dror Margalit, Yuval Trostianetsky, Guy Khatib, Fadi Galun, Meirav Basri, Ronen Computer Vision and Pattern Recognition Robust estimation of the essential matrix, which encodes the relative position and orientation of two cameras, is a fundamental step in structure from motion pipelines. Recent deep-based methods achieved accurate estimation by using complex network architectures that involve graphs, attention layers, and hard pruning steps. Here, we propose a simpler network architecture based on Deep Sets. Given a collection of point matches extracted from two images, our method identifies outlier point matches and models the displacement noise in inlier matches. A weighted DLT module uses these predictions to regress the essential matrix. Our network achieves accurate recovery that is superior to existing networks with significantly more complex architectures. |
| title | Consensus Learning with Deep Sets for Essential Matrix Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.17414 |