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

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>"
}