重新审视长时程流式三维重建中的局部上下文

摘要

从极长视频中进行流式3D重建需要在有界内存和计算条件下在线估计相机运动与场景几何。早期流式模型通过有限上下文缓冲区或紧凑的循环状态实现因果、有界成本的推理，但其估计往往随序列增长而退化。近期方法通过将短程上下文与持久化或多层级长程记忆相结合，改善了长程稳定性。我们则采用不同的路线：保持学习到的时间状态严格局部化，并构造预测目标使其独立于序列长度。我们提出ABot-Recon，一种简单的流式模型，仅缓存前11帧的KV特征。它在当前相机坐标系中预测点图，同时输出相邻帧间的相对位姿。这些预测在参考系变化下保持等变性，全局位姿与几何通过顺序组合恢复。为减少累积漂移，轻量级时间细化器利用近期视觉与运动上下文改善相对旋转，组合感知位姿损失则对多步位姿组合进行监督。在具有挑战性的长序列基准上的广泛评估证明了我们局部上下文方法的卓越长程性能。在Oxford Spires数据集上，ABot-Recon实现了4.35米的ATE和0.12°的RPE-R，相较先前最优结果，两项误差均降低约40%。

English

Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation. Early streaming models achieve causal, bounded-cost inference using finite context buffers or compact recurrent states, yet their estimates often deteriorate as sequences grow. Recent methods improve long-horizon stability by coupling short-range context with persistent or multi-level long-range memory. We pursue a different route: we keep the learned temporal state strictly local and formulate predictions whose targets remain independent of sequence length. We present ABot-Recon, a simple streaming model that caches KV features from only the preceding 11 frames. It predicts a point map in the current camera coordinate system together with an adjacent-frame relative pose. These predictions remain equivariant under changes of reference frame, and global poses and geometry are recovered through sequential composition. To reduce accumulated drift, a lightweight temporal refiner improves relative rotations using recent visual and motion context, while a composition-aware pose loss supervises multi-step pose composition. Extensive evaluations on challenging long-sequence benchmarks demonstrate the superior long-horizon performance of our local-context approach. On Oxford Spires, ABot-Recon achieves an ATE of 4.35 m and an RPE-R of 0.12^circ, reducing both errors by approximately 40\% relative to the best prior results.