Super-realtime facial landmark detection and shape fitting by deep regression of shape model parameters

TL;DR

This paper introduces a fast, deep learning-based facial landmark detection method that predicts shape model parameters in a single pass, enabling real-time performance for applications like facial analysis and medical imaging.

Contribution

It integrates PCA-based shape modeling into a neural network with a novel layer, allowing direct, non-iterative prediction of landmarks at high speed.

Findings

Achieves hundreds of frames per second in landmark detection

Outperforms traditional iterative methods in speed and accuracy

Successfully applied to facial and medical image datasets

Abstract

We present a method for highly efficient landmark detection that combines deep convolutional neural networks with well established model-based fitting algorithms. Motivated by established model-based fitting methods such as active shapes, we use a PCA of the landmark positions to allow generative modeling of facial landmarks. Instead of computing the model parameters using iterative optimization, the PCA is included in a deep neural network using a novel layer type. The network predicts model parameters in a single forward pass, thereby allowing facial landmark detection at several hundreds of frames per second. Our architecture allows direct end-to-end training of a model-based landmark detection method and shows that deep neural networks can be used to reliably predict model parameters directly without the need for an iterative optimization. The method is evaluated on different datasets for facial landmark detection and medical image segmentation. PyTorch code is freely available at https://github.com/justusschock/shapenet