# Face Alignment Using K-Cluster Regression Forests With Weighted Splitting

## TL;DR

This paper introduces a face alignment pipeline utilizing novel weighted splitting K-cluster Regression Forests and 3D affine pose regression, achieving significant accuracy improvements on challenging datasets.

## Contribution

The work presents a new weighted splitting method for K-cluster Regression Forests and integrates 3D affine pose regression for better face shape initialization.

## Key findings

- 20% improvement over standard LBF on IBUG dataset
- State-of-the-art accuracy on 300-W dataset
- Effective face shape initialization with 3D pose regression

## Abstract

In this work we present a face alignment pipeline based on two novel methods: weighted splitting for K-cluster Regression Forests and 3D Affine Pose Regression for face shape initialization. Our face alignment method is based on the Local Binary Feature framework, where instead of standard regression forests and pixel difference features used in the original method, we use our K-cluster Regression Forests with Weighted Splitting (KRFWS) and Pyramid HOG features. We also use KRFWS to perform Affine Pose Regression (APR) and 3D-Affine Pose Regression (3D-APR), which intend to improve the face shape initialization. APR applies a rigid 2D transform to the initial face shape that compensates for inaccuracy in the initial face location, size and in-plane rotation. 3D-APR estimates the parameters of a 3D transform that additionally compensates for out-of-plane rotation. The resulting pipeline, consisting of APR and 3D-APR followed by face alignment, shows an improvement of 20% over standard LBF on the challenging IBUG dataset, and state-of-theart accuracy on the entire 300-W dataset.