发表机构
Waseda University; CyberAgent, Inc.（早稻田大学; 株式会社CyberAgent）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低视差和近旋转情况下传统BA法病态问题，提出门控引导的CSS-BA，通过结合CSS和几何感知门控稳定舒尔-LM更新，所有参数保留在优化中，仅限制更新方向，实验显示其优化稳定、姿态精度提高且校准有竞争力。
AI 中文摘要
光束法平差（BA）仍是基于图像的3D重建的关键优化模块，即使在基于学习的流程中也能不断提高几何精度。然而，在低视差和近旋转情况下，传统基于舒尔的列文伯格-马夸尔特（LM）法常出现病态，导致姿态和校准估计不可靠。我们提出门控引导的CSS-BA，它是对舒尔-LM求解器的一种修改，保留经典BA目标和信赖域框架，同时将每次更新限制在几何信息低维子空间。通过结合列空间搜索（CSS）和几何感知门控，该方法稳定了舒尔-LM更新，而不改变估计问题。与关键帧或状态选择方法不同，所有相机和点参数都保留在优化问题中，仅更新方向受限。该方法可直接替代现有BA流程。在一般和具有挑战性的弱几何场景上的实验表明，优化更稳定，相对姿态精度提高，校准性能有竞争力，同时保持重投影质量。
英文摘要
Bundle adjustment (BA) remains a critical refinement module for image-based 3D reconstruction and continues to improve geometric accuracy even in learning-based pipelines. However, in low-parallax and near-rotational regimes, classical Schur-based Levenberg--Marquardt (LM) often becomes ill-conditioned and yields unreliable pose and calibration estimates. We propose Gate-Guided CSS-BA, a solver-side modification of Schur-LM that preserves the classical BA objective and trust-region framework while constraining each update to a geometrically informed low-dimensional subspace. By integrating Column Space Search (CSS) with geometry-aware gating, the method stabilizes the Schur-LM update without altering the estimation problem. In contrast to keyframe or state-selection approaches, all camera and point parameters remain in the optimization problem; only the update direction is restricted. The method serves as a drop-in replacement for existing BA pipelines. Experiments on both generic and challenging weak-geometry scenarios show more stable optimization, improved relative pose accuracy, and competitive calibration behavior while maintaining reprojection quality.
CommentsAccepted at ECCV 2026
