Graph-CoVis: GNN-Based Multi-View Panorama Global Pose Estimation

Negar Nejatishahidin, Will Hutchcroft, Manjunath Narayana, Ivaylo Boyadzhiev, Yuguang Li, Naji Khosravan, Jana Kosecká, Sing Bing Kang

CVPRW 2023 pp. 6459-6468

doi:10.1109/CVPRW59228.2023.00687 /cvprw/2023/nejatishahidin2023cvprw-graphcovis/

Abstract

In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360° panoramas under upright-camera assumption. Recent work has demonstrated the merit of deep-learning for end-to-end direct relative pose regression in 360° panorama pairs [11]. To exploit the benefits of multi-view logic in a learning-based framework, we introduce Graph-CoVis, which non-trivially extends CoVisPose [11] from relative two-view to global multi-view spherical camera pose estimation. Graph-CoVis is a novel Graph Neural Network based architecture that jointly learns the co-visible structure and global motion in an end-to-end and fully-supervised approach. Using the ZInD [4] dataset, which features real homes presenting wide-baselines, occlusion, and limited visual overlap, we show that our model performs competitively to state-of-the-art approaches.

PDF CVPRW Semantic Scholar

Cite

Text

Nejatishahidin et al. "Graph-CoVis: GNN-Based Multi-View Panorama Global Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00687

Markdown

[Nejatishahidin et al. "Graph-CoVis: GNN-Based Multi-View Panorama Global Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/nejatishahidin2023cvprw-graphcovis/) doi:10.1109/CVPRW59228.2023.00687

BibTeX

@inproceedings{nejatishahidin2023cvprw-graphcovis,
  title     = {{Graph-CoVis: GNN-Based Multi-View Panorama Global Pose Estimation}},
  author    = {Nejatishahidin, Negar and Hutchcroft, Will and Narayana, Manjunath and Boyadzhiev, Ivaylo and Li, Yuguang and Khosravan, Naji and Kosecká, Jana and Kang, Sing Bing},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {6459-6468},
  doi       = {10.1109/CVPRW59228.2023.00687},
  url       = {https://mlanthology.org/cvprw/2023/nejatishahidin2023cvprw-graphcovis/}
}