AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909223190790144 |
|---|---|
| author | Watson, Jamie Aleotti, Filippo Sayed, Mohamed Qureshi, Zawar Mac Aodha, Oisin Brostow, Gabriel Firman, Michael Vicente, Sara |
| author_facet | Watson, Jamie Aleotti, Filippo Sayed, Mohamed Qureshi, Zawar Mac Aodha, Oisin Brostow, Gabriel Firman, Michael Vicente, Sara |
| contents | Extracting planes from a 3D scene is useful for downstream tasks in robotics and augmented reality. In this paper we tackle the problem of estimating the planar surfaces in a scene from posed images. Our first finding is that a surprisingly competitive baseline results from combining popular clustering algorithms with recent improvements in 3D geometry estimation. However, such purely geometric methods are understandably oblivious to plane semantics, which are crucial to discerning distinct planes. To overcome this limitation, we propose a method that predicts multi-view consistent plane embeddings that complement geometry when clustering points into planes. We show through extensive evaluation on the ScanNetV2 dataset that our new method outperforms existing approaches and our strong geometric baseline for the task of plane estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08960 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings Watson, Jamie Aleotti, Filippo Sayed, Mohamed Qureshi, Zawar Mac Aodha, Oisin Brostow, Gabriel Firman, Michael Vicente, Sara Computer Vision and Pattern Recognition Extracting planes from a 3D scene is useful for downstream tasks in robotics and augmented reality. In this paper we tackle the problem of estimating the planar surfaces in a scene from posed images. Our first finding is that a surprisingly competitive baseline results from combining popular clustering algorithms with recent improvements in 3D geometry estimation. However, such purely geometric methods are understandably oblivious to plane semantics, which are crucial to discerning distinct planes. To overcome this limitation, we propose a method that predicts multi-view consistent plane embeddings that complement geometry when clustering points into planes. We show through extensive evaluation on the ScanNetV2 dataset that our new method outperforms existing approaches and our strong geometric baseline for the task of plane estimation. |
| title | AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.08960 |