youngLBW / HRN

[CVPR2023] A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images.
https://younglbw.github.io/HRN-homepage/
Apache License 2.0
407 stars 37 forks source link

请问如何获得ground-truth的maps标签? #21

Open Bys35271 opened 1 year ago

Bys35271 commented 1 year ago

已有初始输入图片、对应的面扫网格、低频部分产生的网格M_0; 面扫网格和M_0配准、和原图片对齐之后,原文提到能通过“fitting the image and scan using the loss functions mentioned in Sec. 3.2”来得到deformation map 和 displacement map。 按照这里的阐述,我实在弄不明白具体该如何编码来实现这部分的fitting; fitting的双方是image和scan也有些不解,比如deformation map是为了指导M_0形变成为M_1,直观看来是否应该scan和M_0进行一些操作来获得ground-truth 的 deformation map呢?