Qualcomm® AI HubAI Hub

Facial-Landmark-Detection-Quantized

Facial landmark predictor with 3DMM.

Real‑time 3D facial landmark detection optimized for mobile and edge.

Model RepositoryHugging Face

Technical Details

Input resolution:128x128
Number of parameters:5.424M
Model size:5.314MB

Applicable Scenarios

  • Driver Monitor System
  • Face Tracking

Licenses

Source Model:BSD-3-CLAUSE
Deployable Model:AI Model Hub License

Tags

  • quantized

Supported IoT Devices

  • QCS6490 (Proxy)
  • QCS8550 (Proxy)
  • RB3 Gen 2 (Proxy)

Supported IoT Chipsets

  • Qualcomm® QCS6490 (Proxy)
  • Qualcomm® QCS8550 (Proxy)

Related Models

See all models
View details for the ResNet18 model.

ResNet18

Imagenet classifier and general purpose backbone.

View details for the Facial-Landmark-Detection model.

Facial-Landmark-Detection

Facial landmark predictor with 3DMM.

Looking for more? See models created by industry leaders.

Discover Model Makers