BiaoBiaoLi

The calculation of ground truth in data_loaders.py

3

Thanks your work, In https://github.com/chrischoy/FCGF/blob/master/lib/data_loaders.py M = (self.velo2cam @ positions[0].T @ np.linalg.inv(positions[1].T) @ np.linalg.inv(self.velo2cam)).T Why does the M not be np.linalg.inv(positions[0]) @ positions[1] ? Thanks!!!

Thanks your work !!! I would like to know how to achieve the reconstruction rendering effect like supplementmaterial and showing video.  My reconstruction is at a poor rendering level....

Hi chrischoy: Thanks your work,I want know where is the supplement?

1

Hi chrischoy: Thanks your work,I want know where is the supplement? I want to know the detail of the 3.3. Weighted Procrustes for SE(3),thanks!

how to get the std of FMR in the paper and the rotated experiments？

1

Thanks your work！ I want to know how to get the std of FMR in the paper and the rotated experiments？ because the test.py cannot generate it. 

Find the nearest neighbor and SVD to solve for the transformation

9

Hi yewzijian: Thanks your work,I want ask two questions: 1. As for finding the nearest neighbor: group_idx[sqrdists > radius ** 2] = N group_idx = group_idx.sort(dim=-1)[0][:, :, :nsample] In the...

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

3

### Describe the question. Thanks for your work !! I meet a problem, could you please help me ? I use the resnet example in pytorch case, i test the...