Closed sillybirrrd closed 1 year ago
Thanks for your interest in our work! It's caused by different definitions of the world coordinate system in different datasets. If you wanna train on your own dataset, please align your coordinate system to either People-Snapshot or ZJU-Mocap, and choose the corresponding light setting.
Thanks for your reply, it helps me a lot!
Hi Zhaoxi, Thanks for your great work! It seems like zju-mocap and people-snapshot use different light settings. I'm confused about that, could you please explain that?
If I wanna train the model on my own dataset, which one should I choose? Thanks in advance!