重新审视长时序流3D重建中的局部上下文
Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
浏览论文内容
中文总结 AI 辅助
本文提出ABot-Recon流3D重建模型，仅缓存前11帧KV特征，通过局部上下文减少累积漂移，在Oxford Spires数据集上将ATE、RPE-R误差降低约40%，提升了长时序性能。
中文摘要 AI 辅助
从极长视频中进行流3D重建需要在有限内存和计算资源下在线估计相机运动与场景几何结构。早期流模型通过有限上下文缓冲区或紧凑循环状态实现因果、有限成本的推理，但随着序列长度增加，其估计结果常出现性能退化。近期方法通过将短程上下文与持久或多级长程记忆结合，提升长时序稳定性。本文采用不同思路：将学习到的时间状态严格保持为局部，并构建与序列长度无关的预测目标。我们提出ABot-Recon，一种简单的流模型，仅缓存前11帧的KV特征，预测当前相机坐标系下的点图及相邻帧相对位姿。这些预测在参考帧变化时保持等变性，全局位姿与几何结构通过序列组合恢复。为减少累积漂移，轻量时间细化器利用近期视觉与运动上下文改进相对旋转，同时引入感知组合的位姿损失监督多步位姿组合。在具有挑战性的长序列基准上的大量评估表明，本文的局部上下文方法具备优异的长时序性能：在Oxford Spires数据集上，ABot-Recon的ATE为4.35m，RPE-R为0.12°，较此前最佳结果将两类误差均降低约40%。
英文摘要
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.
发表机构
- Alibaba Group（阿里巴巴集团）
机构由 AI 辅助整理，请以论文原文为准。
