# Realistic face animation generation from videos

arXiv: https://arxiv.org/abs/2103.14984 · HTML: https://mlsanity.com/paper/2103.14984/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 27 Mar 2021.

## Builds on (most cited first, 8 of 8)

- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://mlsanity.com/paper/1803.07835/) (2018)
- [Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network](https://mlsanity.com/paper/1612.04904/) (2016)
- [Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing](https://mlsanity.com/paper/2003.08061/) (2020)
- [Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression](https://mlsanity.com/paper/1703.07834/) (2017)
- [Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition](https://mlsanity.com/paper/1708.02734/) (2017)
- [Subjective and Objective Visual Quality Assessment of Textured 3D Meshes](https://mlsanity.com/paper/2102.03982/) (2021)
- [Fitting 3D Morphable Models using Local Features](https://mlsanity.com/paper/1503.02330/) (2015)

## Built on by (most cited first, 1 of 1)

- [Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction](https://mlsanity.com/paper/2112.14382/) (2021)

## Abstract (arXiv)

3D face reconstruction and face alignment are two fundamental and highly related topics in computer vision. Recently, some works start to use deep learning models to estimate the 3DMM coefficients to reconstruct 3D face geometry. However, the performance is restricted due to the limitation of the pre-defined face templates. To address this problem, some end-to-end methods, which can completely bypass the calculation of 3DMM coefficients, are proposed and attract much attention. In this report, we introduce and analyse three state-of-the-art methods in 3D face reconstruction and face alignment. Some potential improvement on PRN are proposed to further enhance its accuracy and speed.