-
Notifications
You must be signed in to change notification settings - Fork 228
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
camera map #12
Comments
We have update the arxiv with more details, please refer to https://arxiv.org/abs/2008.12272 Sorry for the belated response. Actually, we didn't directly supervise the camera map. Therefore, I can't provide a effective equation to derive the ground truth Camera map from 3dpw. But you may obtain the camare parameter for each person via fitting the back-projected 2D body joints. I can't guarantee the effectiveness but it might worth a try. Thanks for your interests! Have a nice day. |
作者你好,请问在做训练数据的时候,camera map(1x3)是通过3dpw的ground truth中的哪些数据通过什么方式换算过来的呢?可否给你一个具体的公式呢?
The text was updated successfully, but these errors were encountered: