发表机构
ETH Zurich; University of Stuttgart; Microsoft（苏黎世联邦理工学院; 斯图加特大学; 微软）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长上下文流式重建中的漂移问题，提出基于全局描述符检索的闭环检测与SE(3)流形位姿优化方法，实现公里级无漂移重建，性能显著优于现有技术。
AI 中文摘要
前馈基础模型近期展现了卓越的三维重建能力。然而，现有模型在长上下文流式重建中由于误差累积而表现出较大的跟踪漂移。本文重新审视了流式重建基础模型中的闭环问题，以实现准确、无漂移、公里级尺度的重建。具体而言，我们的方法通过全局描述符检索来检测闭环候选，并构建闭环条件窗口以估计闭环帧之间的相对位姿。鉴于我们采用的流式重建骨干网络产生全局一致的尺度，我们在SE(3)流形上优化所有帧位姿，并加入序列约束和闭环约束，从而避免了先前工作中使用的Sim(3)或更高维SL(4)流形上的位姿图优化。大量实验表明，我们的方法在公里级序列上减少了漂移并产生一致的几何结构，显著优于现有技术水平。代码可在以下网址获取：https://this-url。
英文摘要
Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in long-context streaming reconstruction due to error accumulation. In this paper, we revisit loop closure with streaming reconstruction foundation models to enable accurate, drift-free, kilometer-scale reconstruction. Specifically, our method detects loop candidates through global descriptor retrieval, and constructs loop-conditioned windows to estimate the relative poses between looped frames. Given the observation that our adopted streaming reconstruction backbone produces a globally consistent scale, we optimize all frame poses on the SE(3) manifold with sequential and loop closure constraints, avoiding the pose graph optimization on the Sim(3) or higher-dimensional SL(4) manifolds employed in prior works. Extensive experiments show that our method reduces drift and produces consistent geometry on kilometer-scale sequences, significantly outperforming the state of the art. Code is available at https://github.com/MoyangLi00/CLoSeR.git.
CommentsAuthors contributed equally to this work. Author order is interchangeable
