SPengLiang/DID-M3D

the difference between of original paper and this repo

Closed this issue · 2 comments

Hi

I'm curious why the result Car@BEV IoU=0.7[33.91,24.00,19.52] / Car@3D IoU=0.7[33.91 ,24.00, 19.52] in this repo is better than the result Car@BEV IoU=0.7[31.10,22.76, 19.50] / Car@3D IoU=0.7[25.38,17.07,14.06] of original paper?
Is there any difference that makes this improve?

Thanks.

Sorry for the late reply. The released codebase is our re-implementation of the original code in the paper. The core code and idea are the same.

thx, it is an interesting thing.