提出 HorizonStream，解决长序列3D重建中的漂移与崩溃问题。
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
- 设计分层注意力机制，分离长短时几何证据传播
- 支持超万帧序列重建，内存恒定、时间线性增长
- 适合实时3D重建系统开发者和机器人导航研究者
在线3D重建需在因果性和有限内存约束下估计相机位姿与场景几何。现有方法在长序列中常出现漂移、抖动或崩溃。我们发现其根源在于本质的时间异质性：几何证据从短暂对应到长期全局尺度不一，但现有架构施加了统一且病态的影响模式。例如滑动窗口有硬截止，无门控循环与因果注意力导致缓存饱和与尖峰注意力。为此，我们将几何传播形式化为证据影响核，提出 HorizonStream，一种显式分解该核的长时距Transformer。针对长程时间因子，几何线性注意力学习通道级衰减速率，实现有界、多时标几何证据传播；针对短程空间因子，结合时空位置编码的几何局部注意力可实现可靠3D匹配并抑制注意力尖峰。最终，度量读出令牌直接从持续几何状态恢复稳定尺度与刚性位姿。大量实验表明，仅用48帧片段训练的 HorizonStream，可稳定泛化至超过10,000帧的序列，保持恒定内存与线性时间复杂度，达到当前最优在线3D重建性能。
原文摘要 · Abstract (English)
Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures to a fundamental mismatch. Streaming geometry is inherently temporally heterogeneous, with evidence ranging from short-lived correspondences to persistent global scale. However, current architectures impose uniform and pathological influence patterns. For example, sliding windows enforce hard cutoffs, while ungated recurrence and causal attention cause cache saturation and spike-like attention sinks. To resolve this, we formalize geometric propagation as an \emph{evidence influence kernel} and propose HorizonStream, a long-horizon Transformer that explicitly factorizes this kernel. For the long-range temporal factor, Geometric Linear Attention learns channel-wise decay rates to enable bounded, multi-timescale propagation of geometric evidence. For the short-range spatial factor, Geometric Local Attention with Spatiotemporal RoPE performs reliable 3D matching while suppressing attention sinks. Finally, Metric Readout Tokens recover stable scale and rigid pose directly from the persistent geometric state. Extensive experiments show that HorizonStream, trained on only 48-frame clips, generalizes stably to sequences exceeding 10,000\ frames with constant memory and linear time, achieving state-of-the-art streaming 3D reconstruction performance. Project Page: https://3dagentworld.github.io/horizonstream/
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。