Zhenjun Zhao (@zhenjun_zhao)
2026-01-28 | ❤️ 103 | 🔁 14 | 💬 0
VGGT-SLAM 2.0: Real time Dense Feed-forward Scene Reconstruction
Dominic Maggio, @lucacarlone1
tl;dr: no 15 DoF alignment in VGGT-SLAM; keyframes as nodes+intra-/inter-submap edges→factor graph; attention layers in VGGT→image retrieval verification
https://arxiv.org/abs/2601.19887 https://x.com/zhenjun_zhao/status/2016476377713709465/photo/1
📄 원문 내용
[2601.19887] VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction
Abstract page for arXiv paper 2601.19887: VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction
미디어
🔗 Related
- gpa-vggt-adapting-vggt-to-large-scale-localization-by-self-s — 같은 저자 @zhenjun_zhao
- maggio-and-carlone-vggt-slam-20-real-time-dense-feed-forward — 도메인: Vision/3D, Reconstruction
- 1n-rotary-position-embeddings-rope-are-ubiquitous-across-tra — 도메인: Vision/3D
- rs-vio — 도메인: Vision/3D, Reconstruction
- googledeepmind-i-have-a-feature-request---please-add-multivi — 도메인: Vision/3D, Reconstruction