Gaze Detection

Class: GazeBlockV1

Source: inference.core.workflows.core_steps.models.foundation.gaze.v1.GazeBlockV1

Run L2CS Gaze detection model on faces in images.

This block can: 1. Detect faces in images and estimate their gaze direction 2. Estimate gaze direction on pre-cropped face images

The gaze direction is represented by yaw and pitch angles in degrees.

Type identifier

Use the following identifier in step "type" field: roboflow_core/gaze@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
do_run_face_detection	bool	Whether to run face detection. Set to False if input images are pre-cropped face images..	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Gaze Detection in version v1.

• inputs: Image Threshold, Reference Path Visualization, Depth Estimation, Bounding Box Visualization, Background Color Visualization, Icon Visualization, Dynamic Zone, Roboflow Custom Metadata, Local File Sink, VLM as Classifier, Polygon Visualization, Trace Visualization, Identify Outliers, VLM as Classifier, Ellipse Visualization, Pixelate Visualization, SIFT, Grid Visualization, Dot Visualization, Camera Focus, Classification Label Visualization, Stitch Images, Model Monitoring Inference Aggregator, Detections Consensus, Line Counter Visualization, Image Blur, SIFT Comparison, Email Notification, Keypoint Visualization, Polygon Zone Visualization, Model Comparison Visualization, Crop Visualization, Corner Visualization, Triangle Visualization, Absolute Static Crop, Stability AI Image Generation, Image Contours, Dynamic Crop, Twilio SMS Notification, Stability AI Inpainting, JSON Parser, Image Slicer, Webhook Sink, QR Code Generator, Stability AI Outpainting, Camera Calibration, Image Convert Grayscale, Image Preprocessing, Circle Visualization, SIFT Comparison, Roboflow Dataset Upload, Blur Visualization, VLM as Detector, Identify Changes, VLM as Detector, Color Visualization, PTZ Tracking (ONVIF).md), Relative Static Crop, Halo Visualization, Image Slicer, Perspective Correction, Mask Visualization, Slack Notification, Label Visualization, Roboflow Dataset Upload
• outputs: Bounding Box Visualization, Background Color Visualization, Roboflow Custom Metadata, Icon Visualization, Dynamic Zone, Detections Transformation, Florence-2 Model, Detections Filter, Trace Visualization, Byte Tracker, Pixelate Visualization, Ellipse Visualization, OpenAI, Dot Visualization, Model Monitoring Inference Aggregator, Detections Consensus, Line Counter Visualization, Detections Classes Replacement, Anthropic Claude, Keypoint Visualization, Template Matching, Model Comparison Visualization, Triangle Visualization, Crop Visualization, Corner Visualization, Dynamic Crop, Webhook Sink, OpenAI, Camera Calibration, Circle Visualization, Llama 3.2 Vision, Roboflow Dataset Upload, Segment Anything 2 Model, Distance Measurement, Blur Visualization, Velocity, Detection Offset, Florence-2 Model, Color Visualization, PTZ Tracking (ONVIF).md), Google Gemini, Detections Merge, Label Visualization, Roboflow Dataset Upload

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Gaze Detection in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • do_run_face_detection (boolean): Whether to run face detection. Set to False if input images are pre-cropped face images..

• output

  • face_predictions (keypoint_detection_prediction): Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object.
  • yaw_degrees (float): Float value.
  • pitch_degrees (float): Float value.

Example JSON definition of step Gaze Detection in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/gaze@v1",
    "images": "$inputs.image",
    "do_run_face_detection": "<block_does_not_provide_example>"
}