Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR (Long-context Geometric Reconstruction), a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization. LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning. To manage the critical challenge of coherence across chunk boundaries, we propose a learning-based hybrid memory module. This dual-component system combines a parametric Test-Time Training (TTT) memory to anchor the global coordinate frame and prevent scale drift, alongside a non-parametric Sliding Window Attention (SWA) mechanism to preserve uncompressed context for high-precision adjacent alignment. Remarkably, this memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference. Evaluated across standard benchmarks and a newly repurposed VBR dataset with sequences of up to 19k frames, LoGeR substantially outperforms prior state-of-the-art feedforward methods--reducing ATE on KITTI by over 74%--and achieves robust, globally consistent reconstruction over unprecedented horizons.

翻译：前馈几何基础模型在短窗口重建方面表现优异，但将其扩展至分钟级视频时，受限于二次注意力复杂度或循环设计中有限的有效内存。本文提出LoGeR（长上下文几何重建），一种无需后优化即可将稠密三维重建扩展至极长序列的新型架构。LoGeR以分块方式处理视频流，利用强双向先验实现高保真度的块内推理。为应对跨块边界连贯性这一关键挑战，我们提出基于学习的混合内存模块。该双组件系统结合了参数化测试时训练（TTT）内存以锚定全局坐标系并防止尺度漂移，以及非参数化滑动窗口注意力（SWA）机制以保留未压缩的上下文，实现高精度相邻对齐。值得注意的是，该内存架构使LoGeR能够在128帧的序列上进行训练，并在推理时泛化至数千帧。通过在标准基准和重新构建的VBR数据集（序列长达19k帧）上进行评估，LoGeR显著优于现有最先进的前馈方法——在KITTI数据集上降低ATE超过74%——并在前所未有的时间跨度上实现了鲁棒且全局一致的重建。