mlsanityData to 7 Oct 2026

Attention Mesh: High-fidelity Face Mesh Prediction in Real-time

arXiv 2006.10962 ↗First posted 19 Jun 2020cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

We present Attention Mesh, a lightweight architecture for 3D face mesh prediction that uses attention to semantically meaningful regions. Our neural network is designed for real-time on-device inference and runs at over 50 FPS on a Pixel 2 phone. Our solution enables applications like AR makeup, eye tracking and AR puppeteering that rely on highly accurate landmarks for eye and lips regions. Our main contribution is a unified network architecture that achieves the same accuracy on facial landmarks as a multi-stage cascaded approach, while being 30 percent faster.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 6; 2024: 8; 2025: 7; 2026: 3.

30 papers.

Sort:

By area:

  1. 2022Towards Metrical Reconstruction of Human Facescited by 165
  2. 20223D face reconstruction with dense landmarkscited by 70
  3. 20243D Face Tracking from 2D Video through Iterative Dense UV to Image Flowcited by 20
  4. 2025Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstructioncited by 20
  5. 2023MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animationcited by 8
  6. 2022PhoMoH: Implicit Photorealistic 3D Models of Human Headscited by 7
  7. 2024Engagement Measurement Based on Facial Landmarks and Spatial-Temporal Graph Convolutional Networkscited by 7
  8. 2024T-FAKE: Synthesizing Thermal Images for Facial Landmarkingcited by 7
  9. 2024PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generationcited by 5
  10. 2022Less is More: Facial Landmarks can Recognize a Spontaneous Smilecited by 3
  11. 2023Multi-Camera Lighting Estimation for Photorealistic Front-Facing Mobile Augmented Realitycited by 3
  12. 2023Automated Detection of Cat Facial Landmarkscited by 3
18 more
  1. 2024Face-GPS: A Comprehensive Technique for Quantifying Facial Muscle Dynamics in Videoscited by 3
  2. 2026SemanticFace: Semantic Facial Action Estimation via Semantic Distillation in Interpretable Spacecited by 2
  3. 2022ReViSe: Remote Vital Signs Measurement Using Smartphone Cameracited by 1
  4. 2023Low-cost Geometry-based Eye Gaze Detection using Facial Landmarks Generated through Deep Learningcited by 1
  5. 2024CIA: Controllable Image Augmentation Framework Based on Stable Diffusioncited by 1
  6. 2025WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalizationcited by 1
  7. 2022Detection of (Hidden) Emotions from Videos using Muscles Movements and Face Manifold Embeddingcited by 0
  8. 2023Facial Reenactment Through a Personalized Generatorcited by 0
  9. 2023SPHEAR: Spherical Head Registration for Complete Statistical 3D Modelingcited by 0
  10. 2024Real-time estimation of overt attention from dynamic features of the face using deep-learningcited by 0
  11. 2024An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosiscited by 0
  12. 2025DIPSER: A Dataset for In-Person Student Engagement Recognition in the Wildcited by 0
  13. 2025OPEN: A Benchmark Dataset and Baseline for Older Adult Patient Engagement Recognition in Virtual Rehabilitation Learning Environmentscited by 0
  14. 2025JOLT3D: Joint Learning of Talking Heads and 3DMM Parameters with Application to Lip-Synccited by 0
  15. 2025Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generationcited by 0
  16. 2025HadaSmileNet: Hadamard fusion of handcrafted and deep-learning features for enhancing facial emotion recognition of genuine smilescited by 0
  17. 2026Localize, Don't Beautify: Client-Side Control of Image-Editing APIs for Cosmetic Surgery Previewscited by 0
  18. 2026Complementary rPPG-Derived and Lip-Region Frequency Cues for Talking-Face Deepfake Detectioncited by 0