发表机构
Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院自动化研究所; 中国科学院大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对全局运动结构重建中平移平均的挑战，提出混合显式平移平均框架，结合相对平移与特征轨迹，经多步处理估计相机位置和3D点，最后完整束调整，实验表明该方法在准确性、鲁棒性和可扩展性上优于现有方法。
AI 中文摘要
全局运动结构重建（SfM）在效率和误差分布方面优于增量方法。然而，平移平均任务仍然具有挑战性。许多现有方法仅依赖相对平移或特征轨迹，在共线相机运动下会退化或易受异常值影响。本文提出了一种新颖的混合显式平移平均框架，结合了相对平移和特征轨迹。具体步骤包括：利用全局相机旋转细化相对平移并去除全局不一致的相对平移；采用基于凸距离的目标函数估计初始相机位置和3D点，再用基于非双线性角度的目标函数进行细化；通过基于有界角度的细化和基于重投影的束调整，利用选定特征轨迹稳健地细化相机旋转和位置；最后使用所有可靠特征轨迹进行完整的束调整以细化相机参数和3D点。在各种顺序和无序真实世界数据集上的大量实验证明了该方法具有卓越的准确性、鲁棒性和可扩展性，在准确性和计算效率上均优于现有方法。
英文摘要
Global Structure-from-Motion (SfM) offers advantages over incremental methods in terms of efficiency and error distribution. However, the task of translation averaging remains challenging. Many existing methods rely solely on relative translations or feature tracks, which either degrade under collinear camera motion or are susceptible to outliers. In this paper, we propose a novel hybrid explicit translation averaging framework that incorporates both relative translations and feature tracks. Specifically, we first refine the relative translations using global camera rotations and remove globally inconsistent relative translations. Next, we employ convex distance-based objective functions to estimate the initial camera positions and 3D points, followed by refinement using a non-bilinear angle-based objective function. Furthermore, since camera rotations are fixed during translation averaging, inaccurate camera rotations can severely limit the accuracy of camera positions. To address this issue, we then robustly refine both camera rotations and camera positions with selected feature tracks through bounded angle-based refinement and subsequent reprojection-based bundle adjustment. In this step, feature tracks are selected to maintain a balanced spatial distribution and improve optimization efficiency. Finally, we perform a complete bundle adjustment using all reliable feature tracks to refine the camera parameters and 3D points. Extensive experiments on various sequential and unordered real-world datasets demonstrate the superior accuracy, robustness, and scalability of our approach, outperforming state-of-the-art methods in both accuracy and computational efficiency.
