用经典SLAM追踪+生成模型建图，实现更精准的尺度一致重建。
ScaRF-SLAM: Scale-Consistent Reconstruction with Feed-Forward Models and Classical Visual SLAM
- 分离追踪与建图：用传统SLAM保证定位稳定，仅用生成模型负责建图。
- 重建误差低至每10米2厘米，比现有方法提升10%-20%精度。
- 适合需要高精度三维重建的机器人、AR/VR应用，尤其在大场景中表现优。
近期工作尝试将SLAM与几何基础模型（GFMs）融合，但直接使用GFM预测进行跟踪对模型能力与不确定性极为敏感，几何误差会反向影响姿态估计。为此，我们提出一种解耦框架：采用经典特征式SLAM实现鲁棒低延迟追踪，仅用GFMs负责建图。通过将建图锚定于SLAM输出的位姿，并跨深度尺度优化，避免将GFM预测误差传入姿态估计，同时施加几何约束于重建结果。系统从多个带位姿的关键帧构建子地图，通过轻量级帧与子地图尺度优化保证尺度一致性；并在每个子地图内执行基于投影的点云融合，实时更新子地图以反映特征式SLAM的轨迹修正。为评估方法性能，我们引入一个具有丰富回环、建筑级规模的室内数据集，配备精确传感器轨迹与激光雷达真值。实验表明，本方法在轨迹精度上表现优异，重建精度较现有方法提升10%-20%，在建筑级数据集上每10米重建误差约2厘米；在大规模室外数据集上，每30米误差达10厘米（相对于激光雷达真值模型）。代码与数据集：https://github.com/ori-drs/ScaRF-SLAM
原文摘要 · Abstract (English)
Recent works have explored unifying SLAM with geometric foundation models (GFMs). However, directly using GFM predictions for tracking is highly sensitive to model capability and uncertainty, as geometric inaccuracies in the predictions can adversely affect pose estimation. To address this limitation, we propose a decoupled framework that integrates classical feature-based SLAM with GFMs, which achieves higher quality and more consistent dense reconstruction. In brief, we use classical visual SLAM for robust low-latency tracking and use GFMs exclusively for mapping. By anchoring mapping to poses produced by the SLAM module and optimizing across depth scales, the proposed design avoids propagating inaccuracies from GFM predictions into pose estimation while imposing geometric constraints on the reconstruction. The system builds submaps from multiple posed keyframes and enforces scale consistency via lightweight frame and submap scale optimization. It also performs projection-based point cloud fusion within each submap, and updates submaps online to reflect trajectory updates from the feature-based SLAM. To evaluate tracking and reconstruction of our method, we introduce a loop-rich, building-scale indoor dataset with accurate sensor trajectories and LiDAR ground-truth. Experiments show that our approach achieves superior trajectory accuracy while improving reconstruction precision by 10%-20% over existing methods, with about 2 cm reconstruction error per 10 m chunk on building-scale dataset. On large-scale outdoor datasets, it attains 10 cm error per 30 m chunk (w.r.t LiDAR ground-truth models). Code and dataset: https://github.com/ori-drs/ScaRF-SLAM
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。