Hold-Out Self-Validation Cannot Certify the Accuracy of Photogrammetric Reconstructions
Overview
This research paper evaluates hold-out self-validation as a substitute for independent accuracy checks in photogrammetric reconstructions used for inspection.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · reconstructions tested: 40 other · Basis not reported
“on ETH3D and EuRoC, and on 30 IMC 2025 scenes. The standard form re-localises each withheld image only against points seen by at least two retained images. Its score saturates. It stayed at 1.00 in all 40 thinned reconstructions while camera-position error varied by a factor of up to 5.9 within one capture. It also scored 1.00 on a corrupted model with only one of 226 cameras within 5 m. Reprojection error ranked som”
Exact source · revision 1Source owner not reported
Reported quantity · corrupted runs evaluated: 18 other · Basis not reported
“e of the worst models best. A few lost cameras can raise the least-squares RMSE to the size of the block, so we also evaluate with a robust alignment. Taking the correspondences from the verified matches lowered the score below 0.95 in 14 of 18 corrupted runs, against 4 for the standard form and 10 when its failed resections count as errors, with all seven nominal runs at 1.00. Mapping the block again without the wit”
Exact source · revision 1Source owner not reported
Reported quantity · nominal runs: 7 other · Basis not reported
“e of the worst models best. A few lost cameras can raise the least-squares RMSE to the size of the block, so we also evaluate with a robust alignment. Taking the correspondences from the verified matches lowered the score below 0.95 in 14 of 18 corrupted runs, against 4 for the standard form and 10 when its failed resections count as errors, with all seven nominal runs at 1.00. Mapping the block again without the wit”
Exact source · revision 1Source owner not reported
Reported quantity · IMC 2025 scenes: 30 other · Basis not reported
“on ETH3D and EuRoC, and on 30 IMC 2025 scenes. The standard form re-localises each withheld image only against points seen by at least two retained images. Its score saturates. It stayed at 1.00 in all 40 thinned reconstructions while camera-position error varied by a factor of up to 5.9 within one capture. It also scored 1.00 on a corrupted model with only one of 226 cameras within 5 m. Reprojection error ranked som”
Exact source · revision 1Source owner not reported
Reported quantity · correspondences from verified matches: 14 other · Basis not reported
“e of the worst models best. A few lost cameras can raise the least-squares RMSE to the size of the block, so we also evaluate with a robust alignment. Taking the correspondences from the verified matches lowered the score below 0.95 in 14 of 18 corrupted runs, against 4 for the standard form and 10 when its failed resections count as errors, with all seven nominal runs at 1.00. Mapping the block again without the wit”
Exact source · revision 1Source owner not reported
Reported quantity · failed resections count as errors: 10 other · Basis not reported
“e of the worst models best. A few lost cameras can raise the least-squares RMSE to the size of the block, so we also evaluate with a robust alignment. Taking the correspondences from the verified matches lowered the score below 0.95 in 14 of 18 corrupted runs, against 4 for the standard form and 10 when its failed resections count as errors, with all seven nominal runs at 1.00. Mapping the block again without the wit”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalHold-Out Self-Validation Cannot Certify the Accuracy of Photogrammetric Reconstructions
This research paper evaluates hold-out self-validation as a substitute for independent accuracy checks in photogrammetric reconstructions used for inspection.
Event coverage history
Current attention 3·Peak within the comparable range 4（2026-11-10 16:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).