# Deep Energies for Estimating Three-Dimensional Facial Pose and Expression

## TL;DR

This paper introduces a machine learning approach that automatically detects key facial features and uses deep energies to accurately estimate 3D facial pose and expression, reducing manual effort and subjectivity.

## Contribution

It presents a novel method combining neural network-based detection with deep energy minimization for 3D facial estimation, bypassing manual rotoscope curves.

## Key findings

- Automatic keypoint detection on images and renders
- Elimination of subjective manual annotations
- Improved accuracy in 3D facial pose estimation

## Abstract

While much progress has been made in capturing high-quality facial performances using motion capture markers and shape-from-shading, high-end systems typically also rely on rotoscope curves hand-drawn on the image. These curves are subjective and difficult to draw consistently; moreover, ad-hoc procedural methods are required for generating matching rotoscope curves on synthetic renders embedded in the optimization used to determine three-dimensional facial pose and expression. We propose an alternative approach whereby these curves and other keypoints are detected automatically on both the image and the synthetic renders using trained neural networks, eliminating artist subjectivity and the ad-hoc procedures meant to mimic it. More generally, we propose using machine learning networks to implicitly define deep energies which when minimized using classical optimization techniques lead to three-dimensional facial pose and expression estimation.