Skip to content

modifiedl repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).

License

Notifications You must be signed in to change notification settings

raja-kumar/DAD-3DHeads

 
 

Repository files navigation

DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image

Paper Conference Project WebPage

Please refer to original readme of the repo to setup the DAD-3DHeads. I have modified this read for my work

Introduction

I intended to use DADNet for dense 2D landmark detection. It performs well on DAD-3DHeads dataset but performance deteriorates when face is only a part of the image. Check Demo section. I used mediapipe facial detector and then passed the detected face to DADNet. The predicted 2D landmarks are then projected back on the original image. See demo section for details

Installation

  • Step1: Set up DADNet using the intructions here
  • Step2: pip install mediapipe (pip install mediapipe-silicon for mac silicon)

Demo

Check this notebook

About

modifiedl repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 72.9%
  • Python 27.1%