Peter
Peter
When I entered the training command, the program did not respond. How can I solve it 
I used my own dataset and then inferred using the test.py code, the result of the reconstruction is clearer, but another issue that arose is that the generated result looks...
Recently, there have been some styles of decoupling work. But the model cannot be generalized. I am trying to use pretrained methods to obtain the style space and laten code...
QQGroup:975690475
Thank you for your excellent work. I would like to know what algorithm you used when fitting 3mm using 68 key points. https://github.com/yfeng95/face3d/blob/master/examples/2_3dmm.py#L75
I found that in your work, facial expressions are generated by specifying numerical values. I tried to transfer the expression boundaries of [IdInvert](https://github.com/genforce/idinvert), but I found that it seemed to...
How are the data in mfcc and face key point landmark files related and whether they are time aligned |--train |---landmark |---dataSet-M030 --landmark ---mfcc
I used the command you gave. The generated image is very dark. I trained for 10k rounds. Is this normal. Or you can give the record of loss value in...
First of all, thank you for your excellent work. May I ask whether the key point estimation mentioned in your paper has the same physical meaning as face landmarks. I...
建群交流
因为编译环境问题,会浪费很多时间,我建了个群,大家一起交流。企鹅群号: 更新:研究方向改变,所以群已经改变用途,不再公布