{"ID":2837904,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18290","arxiv_id":"2511.18290","title":"SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes","abstract":"3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times. In this paper, we propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction. To maintain global consistency in large-scale scenes, SwiftVGGT performs loop closure without relying on the external Visual Place Recognition (VPR) model. This removes redundant computation and enables accurate reconstruction over kilometer-scale environments. Furthermore, we propose a simple yet effective point sampling method to align neighboring chunks using a single Sim(3)-based Singular Value Decomposition (SVD) step. This eliminates the need for the Iteratively Reweighted Least Squares (IRLS) optimization commonly used in prior work, leading to substantial speed-ups. We evaluate SwiftVGGT on multiple datasets and show that it achieves state-of-the-art reconstruction quality while requiring only 33% of the inference time of recent VGGT-based large-scale reconstruction approaches.","short_abstract":"3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow i...","url_abs":"https://arxiv.org/abs/2511.18290","url_pdf":"https://arxiv.org/pdf/2511.18290v1","authors":"[\"Jungho Lee\",\"Minhyeok Lee\",\"Sunghun Yang\",\"Minseok Kang\",\"Sangyoun Lee\"]","published":"2025-11-23T05:03:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false}