Daniel Mao

@wungemach To my understanding, the final output of PRNet is the U-V position map which includes 3-D coordinate of vertex corresponding to face model. How can 2-D landmarks be obtained...

@sdlpkxd hey I am very interested in the underlying application 'Face swap' but I have no experience about it. Would you opensorce your demo about face swap and I am...

Hi is the your implementstion sucessful? @SeeU1119

@PeiliangLi hi, I am new to slam and very appreciate for your excellent work. And I am confused by the extrinsic parameter calibration. As said in paper, the rotation and...

@TalentedMUSE Hey is it any chance for you to share with your code?

@TalentedMUSE Hey is is any chance for you to share your code?

@zuoqing1988 左博，106个点与68个点可以对应的吗？在网上找不着这两者之间的映射，也就是两者没有对应的点吗？那我是不是只能用人脸检测的结果再接第三方（例如dlib）的68个关键点算法了呢？

@zuoqing1988 我目前的情况是只有与68个关键点映射的三维点云数据去做重建和blendshape，106个点的好像在眉毛还有一些地方和68个点不是精确对应的吧，也就是我从106个点把接近的68个点提取出来，会导致我重建的精度有问题的吧？

@chenhan510 Hi, did you solve the problem finally?