Research
CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction
arXiv:2610.01927v1 Announce Type: new Abstract: Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in lo
arXiv:2610.01927v1 Announce Type: new 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.
Related
- FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views
- SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers
- Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
- SharpSplat: Edge-Regularized 3D Gaussian Splatting for High Fidelity Urban Building Reconstruction from UAV images
- Self-Improving 4D Perception via Self-Distillation
Source: arXiv cs.CV | 2026-10-02