BiaoBiaoLi

Results 7 comments of BiaoBiaoLi

The calculation of ground truth in data_loaders.py

I ask here， https://github.com/XuyangBai/D3Feat/issues/31

Find the nearest neighbor and SVD to solve for the transformation

ok,thanks

Find the nearest neighbor and SVD to solve for the transformation

Thanks your answer,I also want to konw the the if the codes of RPM in your paper is open source.

Find the nearest neighbor and SVD to solve for the transformation

Sorry,I don't make myself clear. I want to konw if the codes of RPM(New algorithms for 2D and 3D point matching: pose estimation and correspondence) in your paper is open...

Find the nearest neighbor and SVD to solve for the transformation

Yes,thank you so much, I find it for a long time.

Find the nearest neighbor and SVD to solve for the transformation

Hi yewzijian: Thanks your work,I also want to know why sinkhorn use logarithms to normalize the matrices? what i read the original RPM is showed below, it does not use...

why the speed of any loader in ["pytorch", "dali", "dali_proxy"] is the same in imagenet val dataset ?

thanks your help. I will test it without any data processing. and i want to know if the parallel = true in https://github.com/NVIDIA/DALI/issues/3191 can help me load image faster ?