3DDFA model to Surrey model conversion

zhixuany / HUMBI

This repository contains official code (in MATLAB) for exploring and visualizing HUMBI dataset introduced in the paper "HUMBI: A Large Multiview Dataset of Human Body Expressions" (CVPR 2020).

MIT License

117 stars 8 forks source link

3DDFA model to Surrey model conversion #16

Closed zhouhaic closed 3 years ago

zhouhaic commented 3 years ago

I notice you transformed 3DDFA model to Surrey in Chapter 4.2, and I want to train my network on 3DDFA and HUMBI dataset. So, can you offer some detail about how to did this? Or whether you have a plan to public related code?

Thanks for your work！

Gorokke commented 3 years ago

We heuristically fit the model to another model based on the pre-defined several correspondences (e.g., salient eyes, mouth points) in 3D, and then measure the closest distance in 3D to establish the full correspondences.

Best,