SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing
This work addresses the scalability limitation of transformer-based SLAM to long trajectories, enabling unbounded processing for robotics and autonomous navigation.
The paper introduces SLAMFormer-∞, the first geometric transformer for SLAM that supports unbounded frontend and backend processing without explicit distance limits, using memory conditions for flexible coordinate systems. It achieves superior or competitive performance in trajectory estimation and scene reconstruction, and generalizes to sequences over 17km.
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 $17\mathrm{km}$.