Parskatt / RoMa

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
https://parskatt.github.io/RoMa/
MIT License
622 stars 51 forks source link

question about pos_embed in tiny roma #52

Closed huang583824382 closed 4 months ago

huang583824382 commented 4 months ago

Hi @Parskatt , thanks for your wonderful job! But I have a question regarding calculation of P_lowres. Why are the best_match indices concatenated instead of the best_match scores for calculating the softmax? https://github.com/Parskatt/RoMa/blob/82a3396de7b39eac50b08d628f735140a0e1a7df/romatch/models/tiny.py#L132-L135

Parskatt commented 4 months ago

Lol that seems bugged yeah, it should be cv[best_match] or something like that right? I made tiny roma pretty quickly so might still be bugs. Could you try the correct version?

huang583824382 commented 4 months ago

Lol that seems bugged yeah, it should be cv[best_match] or something like that right? I made tiny roma pretty quickly so might still be bugs. Could you try the correct version?

Yeah I think so, thank you for your reply! Maybe I'll try it later.