Giters

zhengyuf / IMavatar

Official repository for CVPR 2022 paper: I M Avatar: Implicit Morphable Head Avatars from Videos

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

coordinate system of IMavatar output

Zvyozdo4ka opened this issue · comments

commented

Is your project's output would be in the same coordinate system as FLAME?

commented

Yes. IMavatar's output is aligned with FLAME except for a scaling factor.

commented

@zhengyuf could you explain, please,

  1. is it output? or input? i am so confused. Could you explain please what should be the input and what output will we get?
    image

  2. could give a hint how to get point cloud?

commented
  1. I was assuming that the output is the reconstructed head SDF, and the input is the training video.
  2. You can either sample from the mesh, or directly use PointAvatar