vertex index of 2D 68landmark map relationship in 3DDFA 3D reconstruction pointcloud
453875726 opened this issue · 5 comments
I’ve got 68 landmark posistion information using dlib. Now I want to know their corresponding vertexs' index in 3DDFA 3D reconstruction pointcloud. Does anyone knows how it works? Thx!
我使用 dlib 获得了 68 个地标位置信息。现在我想知道它们在 3DDFA 3D 重建点云中对应的顶点索引。有谁知道它是如何工作的？谢谢！
Have you solved it yet?
Yes, But I can't remember clearly.
I read the paper "Face alignment across large poses: A 3d solution" which uses BFM(Basel Face Model).
Therefore I checked https://faces.dmi.unibas.ch/bfm/bfm2019.html.
At last I got an Excel file which shows 68 BFM face pointcloud landmark vertexs responding to 2D face landmarks.
landmarks.xlsx
Sorry, this link cannot be opened, could you check it and send it again
Also, the pose parameter of the 300W-LP dataset is 7 dimensional
However, in the implementation code of the 3DDFA paper, the 12 dimensions of regression are used directly
I don't know the connection, do you know this? There are many people asking this question on github, but I can't find the answer, can you help me
BFM's link is as follow:
https://faces.dmi.unibas.ch/bfm/bfm2019.html
However, I don't know why the demensions of paper and its implementation code is different.
BFM的链接如下： https://faces.dmi.unibas.ch/bfm/bfm2019.html
但是，我不知道为什么纸张的尺寸和它的实现代码不一样。
Ok, thank you. I saw that the code evaluation scheme in 3DDFA only has two-dimensional feature points (NME) error, there is no three-dimensional vertices (NME) error, I learned that the normalization of the calculation of three-dimensional vertices (NME) error is: the three-dimensional outer eye spacing of the face, you know how to find this, its index values are how much?