Questions about pose of dataset
yjhong89 opened this issue · comments
Hi. Thanks for great work!
I have few questsions of dataset.
- Is there any other dataset for training rather than 'Multi-Pie' and '300W-LP'?
- How get ground-truth pose data (camera extrinsic, rotation/translation) for '300W-LP' datasets? Isn't it wild images ?
- I have not downloaded 'Multi-Pie' dataset, but I think this dataset might have gt pose data
Thank you.
Best regards,
YJHong.
For Q1: Facescape dataset, multi-view dataset is expensive and indoor setting
For Q2: We do not use the gt pose, we predict pose and leveraging multi-view geometry consistency.
I do not think so, they have not
@jiaxiangshang
Thanks for replying.
For Q2, then how predict pose vector (rotation, translation) ? Is there any code reference that you would recommend ?
the mgcnet predict the pose actually, you can also see DECA, Deep3DFace......
@jiaxiangshang
Thank you.
These are things that I understand so far.
- We need rotation/translation/depth information to leverage multiview-geometry consistency.
- Since ground-truth rotation/translation/depth information doesn't exist for 300W-LP, and MPIE, estimated pose vectors from 3dmm module (DECA, MGCNET, Deep3DFace) are used for multiview-geometry ? (below Equation)
Yes, that is the main idea of MGCNet... :)
@jiaxiangshang Thank you! It is very clear!