DEEP LEARNING

3DDFA — 3D Face Alignment in Full Pose Range

3DDFA is a neural network that turns to be a new SOTA in the reconstruction of a 3D face model from video

3DDFA — 3D Face Alignment in Full Pose Range
3DDFA — 3D Face Alignment in Full Pose Range
Source: Arxiv
Image for post
Image for post
3 modes of 3D Face Alignment in 3DDFA approach

3DDFA — Network architecture

3DDFA combines cascade regression and convolutional networks. CNN is used as a regressor in a cascading convolutional network. The framework consists of four components: regression functionality, image features, convolutional network structures, and an error function for training the model.

  • On the second stream, the model receives feature anchors with consistent semantics and conducts Pose Adaptive Convolution (PAC) on them
3DDFA — 3D Face Alignment in Full Pose Range
3DDFA — 3D Face Alignment in Full Pose Range
An overview of the two-stream network in 3DDFA. Source: Arxiv

3DDFA — Approach performance evaluation

The researchers compared the proposed 3DDFA with state-of-the-art techniques for 3D facial markup. The models were tested on AFLW and AFLW2000–3D datasets. NME (%) was used as a metric. Below you can see that the proposed approach produces results that are higher or comparable to state-of-the-art.

Image for post
Image for post
The NME(%) of face alignment results on AFLW and AFLW2000–3D with the first and the second best results highlighted. The brackets show the training sets. Source: Arxiv

Original Paper

Interested in Deep Learning?

If you found this article helpful, click the💚 or 👏 button below or share the article on Facebook so your friends can benefit from it too.

Written by

Bioinformatician at Oncobox Inc. (@oncobox). Research Associate at Moscow Institute of Physics and Technology (@mipt_eng).

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store