gpa-vggt-adapting-vggt-to-large-scale-localization-by-self-s

Zhenjun Zhao (@zhenjun_zhao)

2026-01-26 | ❤️ 106 | 🔁 17 | 💬 1

---

GPA-VGGT: Adapting VGGT to Large scale Localization by self-Supervised learning with Geometry and Physics Aware loss

Yangfan Xu, Lilian Zhang, Xiaofeng He, Pengdong Wu, Wenqi Wu, Jun Mao

tl;dr: Self-supervised VGGT

https://arxiv.org/abs/2601.16885 https://x.com/zhenjun_zhao/status/2015744134892421540/photo/1

---

📄 원문 내용

[2601.16885] GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss

Abstract page for arXiv paper 2601.16885: GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss

---

미디어

---

🔗 Related

• vggt-slam-20-real-time-dense-feed-forward-scene-reconstructi — 같은 저자 @zhenjun_zhao
• maggio-and-carlone-vggt-slam-20-real-time-dense-feed-forward — 도메인: Vision/3D, Reconstruction
• rs-vio — 도메인: Vision/3D, Reconstruction
• googledeepmind-i-have-a-feature-request---please-add-multivi — 도메인: Vision/3D, Reconstruction
• 3dgs2-tr-scalable-second-order-trust-region-method-for-3d-ga — 같은 저자 @zhenjun_zhao

Tags

기타