Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911339960598528 |
|---|---|
| author | Deng, Tianchen Wu, Wenhua Wu, Kunzhen Wang, Guangming Zhu, Siting Yuan, Shenghai Chen, Xun Shen, Guole Liu, Zhe Wang, Hesheng |
| author_facet | Deng, Tianchen Wu, Wenhua Wu, Kunzhen Wang, Guangming Zhu, Siting Yuan, Shenghai Chen, Xun Shen, Guole Liu, Zhe Wang, Hesheng |
| contents | Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates. However, the late motion average is often insufficient for effectively integrating spatial information, and its accuracy degrades in complex environments. In this paper, we present the first visual localization framework that performs multi-view spatial integration through an early-fusion mechanism, enabling robust operation in both structured and unstructured environments. Our framework is built upon the VGGT backbone, which encodes multi-view 3D geometry, and we introduce a pose tokenizer and projection module to more effectively exploit spatial relationships from multiple database views. Furthermore, we propose a novel sparse mask attention strategy that reduces computational cost by avoiding the quadratic complexity of global attention, thereby enabling real-time performance at scale. Trained on approximately eight million posed image pairs, Reloc-VGGT demonstrates strong accuracy and remarkable generalization ability. Extensive experiments across diverse public datasets consistently validate the effectiveness and efficiency of our approach, delivering high-quality camera pose estimates in real time while maintaining robustness to unseen environments. Our code and models will be publicly released upon acceptance.https://github.com/dtc111111/Reloc-VGGT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21883 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer Deng, Tianchen Wu, Wenhua Wu, Kunzhen Wang, Guangming Zhu, Siting Yuan, Shenghai Chen, Xun Shen, Guole Liu, Zhe Wang, Hesheng Computer Vision and Pattern Recognition Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates. However, the late motion average is often insufficient for effectively integrating spatial information, and its accuracy degrades in complex environments. In this paper, we present the first visual localization framework that performs multi-view spatial integration through an early-fusion mechanism, enabling robust operation in both structured and unstructured environments. Our framework is built upon the VGGT backbone, which encodes multi-view 3D geometry, and we introduce a pose tokenizer and projection module to more effectively exploit spatial relationships from multiple database views. Furthermore, we propose a novel sparse mask attention strategy that reduces computational cost by avoiding the quadratic complexity of global attention, thereby enabling real-time performance at scale. Trained on approximately eight million posed image pairs, Reloc-VGGT demonstrates strong accuracy and remarkable generalization ability. Extensive experiments across diverse public datasets consistently validate the effectiveness and efficiency of our approach, delivering high-quality camera pose estimates in real time while maintaining robustness to unseen environments. Our code and models will be publicly released upon acceptance.https://github.com/dtc111111/Reloc-VGGT. |
| title | Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.21883 |