mlsanityData to 14 Oct 2026

Blendshapes GHUM: Real-time Monocular Facial Blendshape Prediction

arXiv 2309.05782 ↗First posted 11 Sep 2023cs.CVcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

4 of 19 references.

References · 4

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  3. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  4. 2019Realistic Speech-Driven Facial Animation with GANscited by 142

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SuperFace: Preference-Aligned Facial Expression Estimation Beyond Pseudo Supervisioncited by 0