Preparation with THUman Dataset
tommycwh opened this issue · comments
tommycwh commented
Thank you very much for your work! I would like to train SHERF on THUman dataset. If I am understanding it correctly, it requires generating images from multiple views for each person in the dataset, but I am not clear about how to generate these data using your code. Would you mind giving me more hints on how to do this?
Thanks again!
Shoukang Hu commented
Hi, we use rendered multi-view images of THUman from MPS-NeRF. You can directly download the multi-view images from the link we provide.
tommycwh commented
I see. I misunderstood that there are another dataset generated for SHERF. Thank you for your prompt reply.