fidopt Interactive view
Registration leaderboards

Drone to crewed aerial photographs

1 datasets, 4 test pairs. A method is ranked here when it has a result on every pair of every one of them.

Read before comparing

  • Ranked apart: outside biomedical imaging, kept as a generic 2D registration problem; four test mosaics from two disasters; shared human correction vectors and overlapping sites.

Ranking OfficialResearch

#MethodMean rankCRASAR-U-DROIDs, drone and crewed aerial registration
1vismatch matchers · RoMaGPU2.501.0–6.01
2vismatch matchers · ALIKED + LightGlueGPU3.001.0–6.02
2vismatch matchers · LoFTRGPU3.001.0–6.02
2vismatch matchers · SIFT + LightGlueGPU3.001.0–6.02
5vismatch matchers · XFeatGPU4.501.0–6.05
6vismatch matchers · DISK + LightGlueGPU5.001.0–6.06
1 place in that table, 1 is best2/10 cases done, not ranked yetn/a does not apply not run some cases failed

Under each dataset, the method's place in that dataset's table: 1 is best, the darker the better. The mean rank averages its places over the datasets.

The scores, dataset by dataset

Each score is followed by its change against no registration: green when the method did better, red when it did worse.