Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
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...
| Authors | Jiarong Han, Jincheng Xiong, Yuzhou Liu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 27 August 2026 |
| Last updated at source | 27 August 2026 |
Popularity, last 5 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- acvlab/ABot-ReconModel · cited by
Models and datasets referencing this paper
- acvlab/ABot-ReconModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.