# Blendshapes GHUM: Real-time Monocular Facial Blendshape Prediction

arXiv: https://arxiv.org/abs/2309.05782 · HTML: https://mlsanity.com/paper/2309.05782/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 11 Sep 2023.

## Builds on (most cited first, 4 of 4)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Realistic Speech-Driven Facial Animation with GANs](https://mlsanity.com/paper/1906.06337/) (2019)

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

- [SuperFace: Preference-Aligned Facial Expression Estimation Beyond Pseudo Supervision](https://mlsanity.com/paper/2605.06179/) (2026)

## Abstract (arXiv)

We present Blendshapes GHUM, an on-device ML pipeline that predicts 52 facial blendshape coefficients at 30+ FPS on modern mobile phones, from a single monocular RGB image and enables facial motion capture applications like virtual avatars. Our main contributions are: i) an annotation-free offline method for obtaining blendshape coefficients from real-world human scans, ii) a lightweight real-time model that predicts blendshape coefficients based on facial landmarks.