VGGT-CD decouples cross-temporal registration from dynamic changes using VGGT reconstructions, achieving 44% and 59% lower Absolute Trajectory Error outdoors and indoors on an 11-scene benchmark while running over 6 times faster.
π3: Scalable Permutation- Equivariant Visual Geometry Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VGGT-CD: Training-Free Robust Registration for 3D Change Detection
VGGT-CD decouples cross-temporal registration from dynamic changes using VGGT reconstructions, achieving 44% and 59% lower Absolute Trajectory Error outdoors and indoors on an 11-scene benchmark while running over 6 times faster.