Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction
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 pr...
Jing-Ke Zhou, Chen-Hang Ma, Zhi-Zhou Zhong et al.
· 1 citation