Yongsung Kim

ReSS: Residual-Restoring Sparse Attention for 3D Vision Transformers

3D vision transformers such as VGGT predict camera poses and scene geometry from multi-view images in a single forward pass, but their global attention over all concatenated view tokens dominates computation as the number of views grows. To reduce this cost, SparseVGGT and HeSS sparsify attention at the block level, an...