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

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>"
}