无需真实数据，自检重建模型的几何一致性，但无法衡量精度。
Track-Leakage-Free Hold-Out Self-Validation for Photogrammetric Reconstruction: Protocol, Sensitivity, and Limits
- 用不参与建模的图像重新定位，避免结构泄漏
- 好模型自洽性高（旋转误差中位数0.003度）
- 可发现严重错误，但对整体扭曲无感
自动化摄影测量重建依赖外部测量验证结果正确性。本文提出无轨迹泄漏的留出自验证协议：固定保留部分图像，仅用被保留图像支持的三维点重新定位被剔除视角，确保测试不依赖自身构建的结构。在五个GNSS参考采集数据（含四个RTK固定）、13个ETH3D激光扫描场景、一个EuRoC飞行数据和30个IMC 2025场景上评估。该方法计算稳定：高质量重建自洽性极佳（中位旋转误差0.003度），但不反映真实精度——其置信度在真实误差波动达14.1倍时仍恒为1.00，且在3.4米、4.3米、1.7米/13度的测绘级真值下也保持1.00。它能识别结构破碎（从1.00降至0.96），却无法检测整体一致性的全局扭曲：三个捕获中，模型误差达55-106米时，置信度仍为1.00。在IMC 2025中，该指标区分失败与成功重建（斯皮尔曼相关ρ=0.68），但在成功案例间无排序能力（ρ=0.01）。捕捉层面的连续信号分析统计能力不足且符号不稳定（k=5，95%置信区间[-0.45, +0.75]），负结果非由此所致。因此，该协议仅衡量内部几何一致性：提供定性碎片化警告，而非控制点精度替代方案。
原文摘要 · Abstract (English)
Automated photogrammetric inspection emits metric measurements from reconstructions whose correctness is normally unknown without an external survey. Can a reconstruction estimate its own reliability with no ground truth, and what would such an estimate measure? We formalise a track-leakage-free hold-out protocol: a deterministic image subset is withheld, and each withheld view is re-localised by resection against only those 3D points supported by at least two retained images, so no view is tested against structure it helped create. We evaluate it on five GNSS-referenced captures (four RTK-fixed) across four sites, 13 ETH3D laser-scan scenes, a EuRoC flight, and 30 IMC 2025 scenes. The protocol is computationally well-posed -- good reconstructions score near-perfect self-consistency (median rotation error 0.003 deg) -- but it does not measure accuracy, for a structural rather than statistical reason. It saturates: confidence stays pinned at 1.00 while true error swings 14.1x within a single capture, and holds at 1.00 on survey-grade truth at 3.4 m, 4.3 m, and 1.7 m / 13 deg. It is blind to coherent distortion: corruption that fragments a reconstruction is caught (1.00 -> 0.96), but corruption yielding a single, internally self-consistent, globally distorted model is not -- at three of four captures such models were wrong by 55-106 m at confidence 1.00. On IMC 2025 the same dichotomy appears with no injected degradation: confidence separates failed from successful reconstructions (rho = 0.68) yet ranks nothing among the successful ones (rho = 0.01). A capture-level meta-analysis of the continuous signal is underpowered and sign-unstable (k = 5, 95% CI [-0.45, +0.75]); the negative result does not rest on it. Track-leakage-free hold-out therefore measures internal geometric consistency: a qualitative fragmentation warning, not a substitute for control-point accuracy assessment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。