Kwang Moo Yi (@kwangmoo_yi)
2026-01-28 | ❤️ 71 | 🔁 9 | 💬 1
Maggio and Carlone, “VGGT-SLAM 2.0: Real time Dense Feed-forward Scene Reconstruction”
Improved version of VGGT-based SLAM. What I find really interesting is Layer 22 — it shows correspondences and can be used to test for overlaps! https://x.com/kwangmoo_yi/status/2016576178430353841/photo/1
🔗 링크
미디어
🔗 Related
- vggt-slam-20-real-time-dense-feed-forward-scene-reconstructi — 도메인: Vision/3D, Reconstruction
- googledeepmind-i-have-a-feature-request---please-add-multivi — 도메인: Vision/3D, Reconstruction
- rs-vio — 도메인: Vision/3D, Reconstruction
- gpa-vggt-adapting-vggt-to-large-scale-localization-by-self-s — 도메인: Vision/3D, Reconstruction
- 1n-rotary-position-embeddings-rope-are-ubiquitous-across-tra — 도메인: Vision/3D