# Pix2face: Direct 3D Face Model Estimation

arXiv: https://arxiv.org/abs/1708.09006 · HTML: https://mlsanity.com/paper/1708.09006/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2017.

## Built on by (most cited first, 3 of 3)

- [H3WB: Human3.6M 3D WholeBody Dataset and Benchmark](https://mlsanity.com/paper/2211.15692/) (2022)
- [DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment](https://mlsanity.com/paper/2305.11522/) (2023)
- [3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information](https://mlsanity.com/paper/2406.01196/) (2024)

## Abstract (arXiv)

An efficient, fully automatic method for 3D face shape and pose estimation in unconstrained 2D imagery is presented. The proposed method jointly estimates a dense set of 3D landmarks and facial geometry using a single pass of a modified version of the popular "U-Net" neural network architecture. Additionally, we propose a method for directly estimating a set of 3D Morphable Model (3DMM) parameters, using the estimated 3D landmarks and geometry as constraints in a simple linear system. Qualitative modeling results are presented, as well as quantitative evaluation of predicted 3D face landmarks in unconstrained video sequences.