Light3R-SfM: Towards Feed-forward Structure-from-Motion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916582008029184 |
|---|---|
| author | Elflein, Sven Zhou, Qunjie Agostinho, Sérgio Leal-Taixé, Laura |
| author_facet | Elflein, Sven Zhou, Qunjie Agostinho, Sérgio Leal-Taixé, Laura |
| contents | We present Light3R-SfM, a feed-forward, end-to-end learnable framework for efficient large-scale Structure-from-Motion (SfM) from unconstrained image collections. Unlike existing SfM solutions that rely on costly matching and global optimization to achieve accurate 3D reconstructions, Light3R-SfM addresses this limitation through a novel latent global alignment module. This module replaces traditional global optimization with a learnable attention mechanism, effectively capturing multi-view constraints across images for robust and precise camera pose estimation. Light3R-SfM constructs a sparse scene graph via retrieval-score-guided shortest path tree to dramatically reduce memory usage and computational overhead compared to the naive approach. Extensive experiments demonstrate that Light3R-SfM achieves competitive accuracy while significantly reducing runtime, making it ideal for 3D reconstruction tasks in real-world applications with a runtime constraint. This work pioneers a data-driven, feed-forward SfM approach, paving the way toward scalable, accurate, and efficient 3D reconstruction in the wild. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14914 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Light3R-SfM: Towards Feed-forward Structure-from-Motion Elflein, Sven Zhou, Qunjie Agostinho, Sérgio Leal-Taixé, Laura Computer Vision and Pattern Recognition Machine Learning We present Light3R-SfM, a feed-forward, end-to-end learnable framework for efficient large-scale Structure-from-Motion (SfM) from unconstrained image collections. Unlike existing SfM solutions that rely on costly matching and global optimization to achieve accurate 3D reconstructions, Light3R-SfM addresses this limitation through a novel latent global alignment module. This module replaces traditional global optimization with a learnable attention mechanism, effectively capturing multi-view constraints across images for robust and precise camera pose estimation. Light3R-SfM constructs a sparse scene graph via retrieval-score-guided shortest path tree to dramatically reduce memory usage and computational overhead compared to the naive approach. Extensive experiments demonstrate that Light3R-SfM achieves competitive accuracy while significantly reducing runtime, making it ideal for 3D reconstruction tasks in real-world applications with a runtime constraint. This work pioneers a data-driven, feed-forward SfM approach, paving the way toward scalable, accurate, and efficient 3D reconstruction in the wild. |
| title | Light3R-SfM: Towards Feed-forward Structure-from-Motion |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.14914 |