发表机构
ETH Zurich; Microsoft Spatial AI Lab; Australian National University; Lund University（苏黎世联邦理工学院; 微软空间人工智能实验室; 澳大利亚国立大学; 隆德大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出统一框架扩展光束平差法，将高阶几何关系建模为类相机实体，保留稀疏性并提升稳定性，在相当运行时下生成更丰富三维结构与更高几何精度。
AI 中文摘要
光束平差法（Bundle Adjustment, BA）是三维计算机视觉的基石，受益于数十年稀疏优化与数值方法的进展，最初用于联合优化相机内参、位姿与稀疏三维点。虽有扩展引入线等基元，但整合平行、共面、线框等更丰富几何结构常大幅增加计算成本并降低数值稳定性。本文提出统一框架，将光束平差扩展为联合优化几何特征与高阶关系：先引入分类法，区分带直接二维测量的可扩展几何特征（如点、线）与编码高阶关系的组（如共面、平行等），证明组可在光束平差框架中建模为类相机实体；基于此，提出组约束与跨特征关系（如点线关联）均可通过二维重投影测量表达，通过构建组诱导与跨特征重投影误差，在舒尔补消元下保留经典点基光束平差的稀疏结构，同时避免会劣化条件与稳定性的直接三维正则化。在真实与合成数据集上的实验表明，其运行时性能可与经典仅点光束平差相当，同时生成显著更丰富的三维结构并提升几何精度。
英文摘要
Bundle Adjustment (BA) is a cornerstone of 3D computer vision and has benefited from decades of advances in sparse optimization and numerical methods. It was originally developed for jointly optimizing camera intrinsics, poses and sparse 3D points. While extensions incorporate lines and other primitives, integrating richer geometric structures such as parallelism, coplanarity, or wireframes often introduces significantly increased computational cost and reduced numerical stability. In this paper, we propose a unified framework that extends bundle adjustment to jointly optimize geometric features and higher-order relations. We first introduce a taxonomy that distinguishes scalable geometric features with direct 2D measurements (e.g., points and lines), from groups encoding higher-order relations (e.g., coplanarity, parallelism, etc.), where we show that groups can be modeled as camera-like entities within the bundle adjustment framework. Building on this formulation, we propose that both group constraints and cross-feature relations (i.e., point-line associations) can be expressed through 2D reprojection measurements. By formulating group-induced and cross-feature reprojection errors, we preserve the sparsity structure of classical point-based BA under Schur elimination, while avoiding direct 3D regularization that degrades the conditioning and stability. Experiments on both real-world and synthetic datasets demonstrate runtime performance comparable to classical point-only bundle adjustment, while producing significantly richer 3D structures and improved geometric accuracy.
CommentsTo appear at ECCV 2026. Code available as part of the LIMAP toolbox at https://github.com/cvg/limap/
