SOURCE-LINKED INTELLIGENCE

VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-view images. Despite their promising performance, these models scale quadratically with the number of input views due to their global attention mechanism, resulting in substantial latency for long sequence inputs. There have been some recent efforts to accelerate VGGT, but they primarily focus on reducing \emph{token redundancy} through token merging or key/value sparsification. Our work resolves this bottleneck from a different perspective by in

Read original source ↗ Open in workspace

recordType

paper

region

Global