发表机构
KAIST (Korea Advanced Institute of Science and Technology)（韩国科学技术院（KAIST））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SLIM-init，一种利用线特征和消失点提供鲁棒旋转约束的无结构单目VIO初始化方法，无需3D重建，在退化运动下提升初始化精度与鲁棒性。
AI 中文摘要
精确的初始化对于可靠的视觉惯性里程计（VIO）至关重要，但在退化运动下，初始化问题往往病态。现有方法通常需要限制性的激励运动来确保足够的可观测性，或依赖计算昂贵的3D结构重建，限制了高效和实用的部署。为解决这些局限性，我们提出SLIM-init，一种无结构的单目VIO初始化器，它直接利用跟踪的2D线特征中的几何约束，无需显式的3D地标重建。具体而言，SLIM-init利用线衍生的消失点（VPs）作为平移不变的方向线索，在低视差或平移主导运动等退化场景下提供鲁棒的纯旋转约束。它进一步结合线对极残差来约束平移，以及线法向投影残差来改善线性对齐的条件，提高初始状态估计的准确性和鲁棒性。在公共基准和具有挑战性的自定义退化运动序列上的大量实验表明，与最先进的初始化方法相比，其准确性和鲁棒性均有提升。源代码可在以下网址获取：this https URL。
英文摘要
Accurate initialization is essential for reliable visual-inertial odometry (VIO), but it is often ill-conditioned under degenerate motions. Existing methods typically require restrictive excitation motions to ensure sufficient observability or rely on computationally expensive 3D structure reconstruction, limiting efficient and practical deployment. To address these limitations, we propose SLIM-init, a structureless monocular VIO initializer that directly exploits geometric constraints from tracked 2D line features without explicit 3D landmark reconstruction. Specifically, SLIM-init leverages line-derived vanishing points (VPs) as translation-invariant orientation cues to provide robust rotation-only constraints under degenerate scenarios such as low-parallax or translation-dominant motions. It further incorporates a line epipolar residual to constrain translation and a line-normal projection residual to improve the conditioning of linear alignment, enhancing the accuracy and robustness of initial state estimation. Extensive experiments on a public benchmark and challenging custom degenerate-motion sequences demonstrate improved accuracy and robustness over state-of-the-art initialization methods. The source code is available at: https://github.com/cjunwan/SLIM-init.
Comments8 pages, 5 figures, Accepted to IROS 2026
