fidopt Interactive view
Registration leaderboards

Serial EM, known in-plane deformation

1 datasets, 10 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: same-section synthetic warps; train and test stacks share one animal; no independent anatomical registration truth.
  • 2 datasets of this kind are shown below and not ranked on the official board: their licence does not allow a public leaderboard. The research board (Research, above the ranking) ranks them too.

Ranking OfficialResearch

#MethodMean rankSNEMI3D sections, known in-plane deformation
1vismatch matchers · LoFTRGPU1.501.0–6.01
1vismatch matchers · RoMaGPU1.501.0–6.01
3vismatch matchers · XFeatGPU3.001.0–6.03
4vismatch matchers · ALIKED + LightGlueGPU4.501.0–6.04
4vismatch matchers · SIFT + LightGlueGPU4.501.0–6.04
6vismatch matchers · DISK + LightGlueGPU6.001.0–6.06
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.

2 datasets without a ranked method yet

ISBI 2012 EM sections, known in-plane deformation, CREMI sections, known in-plane deformation.