CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction

arXiv:2610.01927 · cs.CV, cs.RO · Submitted 2026-10-01 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: Authors contributed equally to this work. Author order is interchangeable

Code: https://github.com/MoyangLi00/CLoSeR

License: http://creativecommons.org/licenses/by/4.0/

The gist: Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities.

Terminology

Abstract

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.

Sources

Related papers