实时稠密建图新框架，用记忆机制提升全局一致性。
GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State
- 采用门控更新模块和潜空间记忆，逐帧累积3D信息。
- 在多个数据集上实现高精度重建与实时性能。
- 适合需要长期稳定建图的机器人导航场景。
基于DUSt3R的端到端场景重建在稠密视觉SLAM中展现出良好前景。然而，现有方法多仅利用图像对估计点云，忽视空间记忆与全局一致性。为此，我们提出GRS-SLAM3R，一个无需场景或相机参数先验的端到端SLAM框架，可从RGB图像中进行稠密场景重建与位姿估计。不同于以往基于DUSt3R的框架在所有图像对上运行并预测局部坐标系下的点云，本方法支持序列输入，逐步在全局坐标系中估计度量尺度点云。为增强空间关联一致性，我们引入潜空间状态作为空间记忆，并设计基于Transformer的门控更新模块，持续聚合与追踪跨帧相关3D信息。此外，将场景划分为子地图，在子地图内进行局部对齐，并通过相对约束将所有子地图注册到统一世界坐标系，生成全局一致的地图。在多个数据集上的实验表明，该框架在保持实时性能的同时，实现了更优的重建精度。
原文摘要 · Abstract (English)
DUSt3R-based end-to-end scene reconstruction has recently shown promising results in dense visual SLAM. However, most existing methods only use image pairs to estimate pointmaps, overlooking spatial memory and global consistency.To this end, we introduce GRS-SLAM3R, an end-to-end SLAM framework for dense scene reconstruction and pose estimation from RGB images without any prior knowledge of the scene or camera parameters. Unlike existing DUSt3R-based frameworks, which operate on all image pairs and predict per-pair point maps in local coordinate frames, our method supports sequentialized input and incrementally estimates metric-scale point clouds in the global coordinate. In order to improve consistent spatial correlation, we use a latent state for spatial memory and design a transformer-based gated update module to reset and update the spatial memory that continuously aggregates and tracks relevant 3D information across frames. Furthermore, we partition the scene into submaps, apply local alignment within each submap, and register all submaps into a common world frame using relative constraints, producing a globally consistent map. Experiments on various datasets show that our framework achieves superior reconstruction accuracy while maintaining real-time performance.
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。