UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization 文章

ArXiv CS.CV2026-08-04PAPERen作者: Inha Lee, Dongjae Jeong, Junhee Lee, Kyungdon Joo

详细信息

来源站点
ArXiv CS.CV
作者
Inha Lee, Dongjae Jeong, Junhee Lee, Kyungdon Joo
文章类型
PAPER
语言
en
发布日期
2026-08-04

摘要

arXiv:2608.01706v1 Announce Type: new Abstract: Recent geometric foundation models enable feed-forward inference for SLAM, but their predictions are strongly dependent on the input view set, which leads to geometric inconsistencies and trajectory drift when results are chained over long sequences. Online deployment further exposes a trade-off between the low latency of two-view tracking and the constraint richness of multi-view inference. We introduce UniSim-SLAM, an integrated system that runs lightweight two-view keyframe tracking in the frontend and performs periodic multi-view submap refinement in the backend. To combine predictions defined in heterogeneous local coordinates with inconsistent scales, we formulate a unified multi-level factor graph on $Sim(3)$ that jointly optimizes global keyframe poses and submap poses.

相关事件

暂无数据

相关公司

暂无数据

相关人物

暂无数据