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

arXiv: https://arxiv.org/abs/2006.10962 · HTML: https://mlsanity.com/paper/2006.10962/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2020.

## Built on by (most cited first, 30 of 30)

- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)
- [3D face reconstruction with dense landmarks](https://mlsanity.com/paper/2204.02776/) (2022)
- [3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow](https://mlsanity.com/paper/2404.09819/) (2024)
- [Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction](https://mlsanity.com/paper/2505.00615/) (2025)
- [MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation](https://mlsanity.com/paper/2303.09797/) (2023)
- [PhoMoH: Implicit Photorealistic 3D Models of Human Heads](https://mlsanity.com/paper/2212.07275/) (2022)
- [Engagement Measurement Based on Facial Landmarks and Spatial-Temporal Graph Convolutional Networks](https://mlsanity.com/paper/2403.17175/) (2024)
- [T-FAKE: Synthesizing Thermal Images for Facial Landmarking](https://mlsanity.com/paper/2408.15127/) (2024)
- [PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation](https://mlsanity.com/paper/2412.07754/) (2024)
- [Less is More: Facial Landmarks can Recognize a Spontaneous Smile](https://mlsanity.com/paper/2210.04240/) (2022)
- [Multi-Camera Lighting Estimation for Photorealistic Front-Facing Mobile Augmented Reality](https://mlsanity.com/paper/2301.06143/) (2023)
- [Automated Detection of Cat Facial Landmarks](https://mlsanity.com/paper/2310.09793/) (2023)
- [Face-GPS: A Comprehensive Technique for Quantifying Facial Muscle Dynamics in Videos](https://mlsanity.com/paper/2401.05625/) (2024)
- [SemanticFace: Semantic Facial Action Estimation via Semantic Distillation in Interpretable Space](https://mlsanity.com/paper/2603.14827/) (2026)
- [ReViSe: Remote Vital Signs Measurement Using Smartphone Camera](https://mlsanity.com/paper/2206.08748/) (2022)
- [Low-cost Geometry-based Eye Gaze Detection using Facial Landmarks Generated through Deep Learning](https://mlsanity.com/paper/2401.00406/) (2023)
- [CIA: Controllable Image Augmentation Framework Based on Stable Diffusion](https://mlsanity.com/paper/2411.16128/) (2024)
- [WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization](https://mlsanity.com/paper/2508.19544/) (2025)
- [Detection of (Hidden) Emotions from Videos using Muscles Movements and Face Manifold Embedding](https://mlsanity.com/paper/2211.00233/) (2022)
- [Facial Reenactment Through a Personalized Generator](https://mlsanity.com/paper/2307.06307/) (2023)
- [SPHEAR: Spherical Head Registration for Complete Statistical 3D Modeling](https://mlsanity.com/paper/2311.02461/) (2023)
- [Real-time estimation of overt attention from dynamic features of the face using deep-learning](https://mlsanity.com/paper/2409.13084/) (2024)
- [An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis](https://mlsanity.com/paper/2412.18919/) (2024)
- [DIPSER: A Dataset for In-Person Student Engagement Recognition in the Wild](https://mlsanity.com/paper/2502.20209/) (2025)
- [OPEN: A Benchmark Dataset and Baseline for Older Adult Patient Engagement Recognition in Virtual Rehabilitation Learning Environments](https://mlsanity.com/paper/2507.17959/) (2025)
- [JOLT3D: Joint Learning of Talking Heads and 3DMM Parameters with Application to Lip-Sync](https://mlsanity.com/paper/2507.20452/) (2025)
- [Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation](https://mlsanity.com/paper/2509.02445/) (2025)
- [HadaSmileNet: Hadamard fusion of handcrafted and deep-learning features for enhancing facial emotion recognition of genuine smiles](https://mlsanity.com/paper/2509.18550/) (2025)
- [Localize, Don't Beautify: Client-Side Control of Image-Editing APIs for Cosmetic Surgery Previews](https://mlsanity.com/paper/2608.02841/) (2026)
- [Complementary rPPG-Derived and Lip-Region Frequency Cues for Talking-Face Deepfake Detection](https://mlsanity.com/paper/2609.22284/) (2026)

## 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.