SOURCE-LINKED INTELLIGENCE

Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

We propose LoG-VGGT, a memory-efficient framework for long-sequence 3D reconstruction that balances local temporal modeling with global camera consistency. Instead of relying on full global attention, our method introduces cross-window attention at a small subset of transformer blocks, enabling effective information propagation across adjacent temporal windows while keeping memory usage bounded. To mitigate long-term pose drift, we further design a global camera consistency refinement module, where camera tokens interact with compact register tokens via cross-attention to enforce scene-level c

Read original source ↗ Open in workspace

recordType

paper

region

Global