{"ID":2873590,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07120","arxiv_id":"2509.07120","title":"Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers","abstract":"Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models like VGGT, $π^3$ and MapAnything have demonstrated remarkable performance with relatively simple architectures. However, their scalability is fundamentally constrained by the quadratic complexity of global attention, which imposes a significant runtime bottleneck when processing large image sets. In this work, we empirically analyze the global attention matrix of these models and observe that the probability mass concentrates on a small subset of patch-patch interactions corresponding to cross-view geometric correspondences. Building on this insight and inspired by recent advances in large language models, we propose a training-free, block-sparse replacement for dense global attention, implemented with highly optimized kernels. Our method accelerates inference by more than $3\\times$ while maintaining comparable task performance. Evaluations on a comprehensive suite of multi-view benchmarks demonstrate that our approach seamlessly integrates into existing global attention-based architectures such as VGGT, $π^3$ , and MapAnything, while substantially improving scalability to large image collections.","short_abstract":"Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models like VGGT, $π^3$ and MapAnything have demonstrated remarkable performance with relatively simple architectures. However, their scalability is fundamentally constrained by the...","url_abs":"https://arxiv.org/abs/2509.07120","url_pdf":"https://arxiv.org/pdf/2509.07120v2","authors":"[\"Chung-Shien Brian Wang\",\"Christian Schmidt\",\"Jens Piekenbrinck\",\"Bastian Leibe\"]","published":"2025-09-08T18:16:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\",\"Language Model\"]","has_code":false}