# MobileFace: 3D Face Reconstruction with Efficient CNN Regression

arXiv: https://arxiv.org/abs/1809.08809 · HTML: https://mlsanity.com/paper/1809.08809/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2018.

## Built on by (most cited first, 5 of 5)

- [Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image](https://mlsanity.com/paper/2205.04126/) (2022)
- [Transferable Adversarial Face Attack with Text Controlled Attribute](https://mlsanity.com/paper/2412.11735/) (2024)
- [3D Facial Imperfection Regeneration: Deep learning approach and 3D printing prototypes](https://mlsanity.com/paper/2303.14381/) (2023)
- [Deep-MDS Framework for Recovering the 3D Shape of 2D Landmarks from a Single Image](https://mlsanity.com/paper/2210.15200/) (2022)
- [Face Normal Estimation from Rags to Riches](https://mlsanity.com/paper/2601.01950/) (2026)

## Abstract (arXiv)

Estimation of facial shapes plays a central role for face transfer and animation. Accurate 3D face reconstruction, however, often deploys iterative and costly methods preventing real-time applications. In this work we design a compact and fast CNN model enabling real-time face reconstruction on mobile devices. For this purpose, we first study more traditional but slow morphable face models and use them to automatically annotate a large set of images for CNN training. We then investigate a class of efficient MobileNet CNNs and adapt such models for the task of shape regression. Our evaluation on three datasets demonstrates significant improvements in the speed and the size of our model while maintaining state-of-the-art reconstruction accuracy.