WWWJL

> > The software meshlab will be OK. > > Thx! 你好，有个问题想请教下您，训练前先要准备uv position map gt，我看代码思路是基于同一个BFM模型生成的uv map。不应该是先得到每个图片对应的BFM,再根据BFM得到uv图么，关于gt制作 这一块，您有什么见解吗？

> When I faced that error, there was already a "pncc_code.mat" file in the "Out" folder, so I copied it from it to the "3ddfa" folder and it worked! hello,i...

> Thanks U for you tell me! I have looked the readme and I have run the code smoothly! hello,i have a question,thank you to explain.i have generate the BFM.mat...

Thank you for your reply，Recently, I encountered a problem in reconstructing your paper. According to the training hyperparameters in paper, I trained backbone and head from the beginning with MS1M...

When training the quality model, the loss keeps decreasing. The test is to use your test script, the quality score is all 1. the quality model is trained with the...

The picture is the loss printed when I trained the Quality Model ---Original--- From: ***@***.***> Date: Sun, Jun 20, 2021 20:20 PM To: ***@***.***>; Cc: ***@***.******@***.***>; Subject: Re: [deepcam-cn/FaceQuality] about...

> @WWWJL Does the quality score work with our pretrained model? yes, the quality score work with your pretrained model work!As I said above, the reproduced quality model I trained...

hi,can you release the train code? thanks

> Hi, > > Thanks for your interest in our dataset! We will release the dataset once the dataset creation paper is accepted. Hopefully we can make it public by...