发表机构
University of Oxford; Technical University of Munich; Munich Center for Machine Learning; Hanyang University; Lund University（牛津大学; 慕尼黑工业大学; 慕尼黑机器学习中心; 汉阳大学; 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
本文通过统一评估框架开展受控实验，揭示无需初始化的光束平差法存在优化-重建差距，明确其核心挑战是获取可可靠度量升级的投影重建，为该领域研究提供了实验基础。
AI 中文摘要
无需初始化的光束平差法（InitFree BA）旨在直接从图像观测中恢复相机位姿和场景结构，避免了传统运动恢复结构（SfM）流程的几何初始化阶段。近期基于物体空间误差（OSE）公式和变量投影（VarPro）的方法，在随机相机配置下展现出令人鼓舞的优化性能。然而，现有评估主要衡量优化成功率，尚不清楚低OSE目标是否能生成有效的度量三维重建结果。本文通过统一评估框架对InitFree BA展开实验研究，该框架结合了现有OSE公式的C++实现，以及基于Blender的数据集生成器，可提供精确的真值和受控的相机配置与观测密度。实验揭示了此前被忽视的优化-重建差距：具有相似低OSE值的投影解在度量升级后会产生显著不同的欧氏重建结果。本文确定初始化先验、特征点观测密度和度量升级稳定性是决定重建成功的关键因素。总体而言，研究结果表明InitFree BA的主要挑战不仅是最小化OSE目标，还在于获得可实现可靠度量升级的投影重建。本文提出的基准、实现和分析为计算机视觉领域尚未充分探索的InitFree BA未来研究建立了更坚实的实验基础。项目页面可访问此https URL。
英文摘要
Initialization-free bundle adjustment (InitFree BA) aims to recover camera poses and scene structure directly from image observations, avoiding the geometric initialization stages of conventional structure-from-motion pipelines. Recent methods based on Object-Space Error (OSE) formulations and Variable Projection (VarPro) show encouraging optimization behavior from random camera configurations. However, existing evaluations primarily measure optimization success, leaving unclear whether a low OSE objective yields a valid metric 3D reconstruction. We revisit InitFree BA experimentally through a unified evaluation framework combining a C++ implementation of existing OSE formulations with a Blender-based dataset generator providing exact ground truth and controlled camera configurations and observation densities. Our experiments reveal a previously overlooked optimization--reconstruction gap: projective solutions with similarly low OSE values can lead to substantially different Euclidean reconstructions after metric upgrade. We identify initialization priors, landmark observation density, and metric-upgrade stability as key factors governing reconstruction success. Overall, our results suggest that the main challenge of InitFree BA is not merely minimizing OSE objectives, but obtaining projective reconstructions that admit reliable metric upgrade. We believe that the proposed benchmark, implementation, and analysis establish stronger experimental foundations for future research on initialization-free bundle adjustment, a problem largely unexplored within the computer vision community. Project page is available at https://github.com/simonwebertum/InitFreeBA.git.
