外观
论文arXiv 2608.034292 个月前
SLAMFormer-∞：用于无界前端和后端处理的 Infinite SLAM Transformer
原文链接：SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing（arXiv 2608.03429 · 发布日期：2026-08-04）
SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing
SLAMFormer-∞面向无显式距离界限的SLAM前后端处理，借助记忆条件建模，并在大规模数据集上验证轨迹估计与场景重建。
核心要点
- 目标是支持长距离前端和后端处理且不设显式距离界限，避免依赖首帧锚定表述。
- 方法采用记忆条件为输入帧定义灵活坐标系和尺度，提供更具表达力的结构条件。
- 前端保持高效局部计算，后端以全局一致方式联合优化长距离轨迹和场景几何。
- 实验显示其在大规模数据集的轨迹估计与场景重建中表现优越或高度竞争，并可处理超过17km序列。
验证范围与局限：验证范围为大规模数据集上的轨迹估计、场景重建和超过17km序列；摘要未说明仿真或真机设置。
英文摘要 (Abstract)
We introduce the Infinite SLAM Transformer (SLAMFormer-$\infty$), the first geometric transformer capable of supporting both long-range frontend and backend processing without an explicit distance bound. Instead of relying on a first-frame-anchored formulation, SLAMFormer-$\infty$ employs memory conditions to define flexible coordinate systems and scales for input frames, enabling more expressive structural conditioning. Built upon this formulation, the frontend preserves efficient local computation, while the backend jointly optimizes long-range trajectories and scene geometry in a globally consistent manner. Experimental results demonstrate that SLAMFormer-$\infty$ achieves superior or highly competitive performance in both trajectory estimation and scene reconstruction across large-scale datasets. Notably, SLAMFormer-$\infty$ generalizes to extremely long trajectories, successfully operating on sequences exceeding $17\mathrm{km}$.
作者：Zhijian Fang, Weicheng Zheng, Yijun Yuan, Weibang Wang, Zhuoguang Chen, Chang Sun, Junhao Huang, Kenan Li, Minghui Qin, Hang Zhao
来源
本页事实对应的公开页面，以原文为准。