通过位姿图优化从无位姿图像中学习场景坐标重建
Learning Scene Coordinate Reconstruction from Unposed Images via Pose Graph Optimization
把位姿图优化作为后处理模块接到无监督 SfM 网络（ACE-Zero）的输出上，并用对极几何与光流一致性估计每条相对位姿约束的置信度，做加权优化——这套「学习预测 + 全局几何优化」的混合范式可直接迁移到任何需要从无序图像恢复相机位姿的视觉流程中。
原文依据 we propose a hybrid framework that integrates pose graph optimization (PGO) into ACE-Zero to refine camera poses
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于学习的运动恢复结构方法（如 ACE-Zero）已展现出强大性能，能够在无需真值监督的情况下，从无序图像集合中估计相机位姿与场景坐标。然而，ACE-Zero 缺乏全局一致性与多视图一致性约束，可能导致位姿漂移与错位，在复杂或歧义场景中尤为明显。在本工作中，我们提出一种混合框架，将位姿图优化（PGO）集成到 ACE-Zero 中，以细化相机位姿并抑制错误的细化结果。我们直接从 ACE-Zero 的输出构建位姿图，通过从预测的场景坐标中提取相对位姿约束来实现。此外，我们引入一种不确定性感知的优化策略，利用几何先验（包括跨视图的对极一致性与光流一致性）估计置信度分数。我们的方法提升了位姿估计的鲁棒性与精度，表明全局几何推理能够有效补充运动恢复结构中的基于学习的推理。
英文原文摘要 1065 字符
Learning-based structure-from-motion methods such as ACE-Zero have demonstrated strong performance in estimating camera poses and scene coordinates from unordered image collections without requiring ground truth supervision. However, the lack of global and multi-view consistency constraints in ACE-Zero can lead to pose drift and misalignment, particularly in complex or ambiguous scenes. In this work, we propose a hybrid framework that integrates pose graph optimization (PGO) into ACE-Zero to refine camera poses and suppress incorrect refinements. We construct pose graphs directly from ACE-Zero outputs by extracting relative pose constraints from predicted scene coordinates. Furthermore, we introduce an uncertainty-aware optimization strategy by estimating confidence scores using geometric priors, including epipolar and optical flow consistencies across views. Our approach improves the robustness and accuracy of pose estimation, demonstrating that global geometric reasoning can effectively complement learning-based inference in structure-from-motion.