search

rabbityl / lepard

[CVPR 2022, Oral] Learning Partial point cloud matching in Rigid and Deformable scenes
MIT License
200 stars 25 forks source link

Which recall did you report in the paper? #6

Closed qsisi closed 2 years ago

qsisi commented 2 years ago

Hello! Thanks for open-sourcing this great work, here I got a question about the registration recall reported in the article. From the code : https://github.com/rabbityl/lepard/blob/bcae7f2ee1a2043372f2582b140645f2d6ade9f2/lib/tester.py#L119 It seems that you calculate the pair-level recall instead of the scene-level recall, but in the methods you compared with such as D3Feat or PREDATOR, the metric recall is calculated in scene-level but not in pair-level.

Could you give some hints about it?

rabbityl commented 2 years ago

@qsisi That's indeed a very good point which I did not noticed previously. Yes the pair-level RR is used in our Repo. I re-evaluated Predator's model using the pair-level RR it got: 91.7/62.5 on 3DMatch/3DLoMatch.( i.e. 1.1% increased in 3DMatch). We will update the paper and clarify this.

rabbityl commented 2 years ago

All metrics are updated as pair-level. closing this.