fengq1a0 / fof Goto Github PK

您好，我使用THuman2.0数据，训练150epoch后，得到了如下的结果

请问是什么原因造成的呢？

First of all, thank you for your great work!
Could you please let us know when the code for data preprocessing be uploaded?
Thanks! :)

你好。可以更新生成训练数据的代码吗

Hi,

Thanks for your new idea, I find that you trained the PIFu method with THuman2.0 Dataset. I also train it myself, but the results of the sdf are all 0. I think maybe it is because the mesh in THuman2.0 is not watertight. I wonder how you use THuman2.0 and Twindom dataset training PIFu method.

Looking forward to your reply.

Thanks.

I tried to process the THumans2.0 dataset myself, but when I ran this command “python prt_util.py”, it took hours with no output, and I had no idea if something was wrong. Can you share the processed dataset if possible?

您出色的工作十分令我震撼，但是我有几个问题想要跟您学习一下：
1.您在论文里面提及到了实时问题，并且展示了相关的实时的视频demo，但是我自己对代码进行测试的时候需要的时间是10s左右，我所使用的服务器显卡是您在论文提到的型号，所以这里我不太理解，因为这样的话是属于先对图像进行了初步的建模，随后在调整的嘛，因为我看您的视频demo确实实时的；
2.您在视频里面的实时，是否可以对视频流进行处理呢？那样是否也可以做到实时呢？
谢谢您的宝贵时间