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: Trace Visualization, Contrast Equalization, Detections Consensus, Circle Visualization, Background Color Visualization, Slack Notification, VLM As Classifier, Color Visualization, Image Slicer, Stability AI Inpainting, Reference Path Visualization, Corner Visualization, Local File Sink, JSON Parser, Relative Static Crop, Perspective Correction, Roboflow Dataset Upload, Model Monitoring Inference Aggregator, Image Threshold, Pixelate Visualization, Polygon Visualization, Ellipse Visualization, Email Notification, Label Visualization, VLM As Detector, Image Slicer, Bounding Box Visualization, Crop Visualization, Twilio SMS/MMS Notification, VLM As Detector, Image Blur, Halo Visualization, Icon Visualization, SIFT, Triangle Visualization, Image Contours, Morphological Transformation, Motion Detection, Stitch Images, SIFT Comparison, Heatmap Visualization, Blur Visualization, Polygon Visualization, Mask Visualization, Email Notification, Stability AI Outpainting, Camera Calibration, Dynamic Zone, Line Counter Visualization, Camera Focus, Webhook Sink, Image Convert Grayscale, Twilio SMS Notification, Camera Focus, Classification Label Visualization, Model Comparison Visualization, Roboflow Dataset Upload, Stability AI Image Generation, SIFT Comparison, Polygon Zone Visualization, VLM As Classifier, Grid Visualization, Background Subtraction, Halo Visualization, Keypoint Visualization, QR Code Generator, Identify Outliers, Depth Estimation, Text Display, Dot Visualization, Identify Changes, Roboflow Custom Metadata, PTZ Tracking (ONVIF).md), Dynamic Crop, Image Preprocessing, Absolute Static Crop
• outputs: Trace Visualization, Detections Consensus, Circle Visualization, Background Color Visualization, Color Visualization, Florence-2 Model, OpenAI, Corner Visualization, SAM 3, Detections Transformation, Seg Preview, Detection Offset, Roboflow Dataset Upload, OpenAI, Detections Filter, Model Monitoring Inference Aggregator, Pixelate Visualization, Ellipse Visualization, Label Visualization, Bounding Box Visualization, Crop Visualization, SAM 3, Stitch OCR Detections, Anthropic Claude, Icon Visualization, Triangle Visualization, Anthropic Claude, Detection Event Log, Heatmap Visualization, Blur Visualization, Detections List Roll-Up, SAM 3, OpenAI, Camera Calibration, Detections Classes Replacement, Segment Anything 2 Model, Google Gemini, Velocity, Anthropic Claude, Google Gemini, Google Gemini, Template Matching, Dynamic Zone, Line Counter Visualization, Webhook Sink, Byte Tracker, Model Comparison Visualization, Continue If, Roboflow Dataset Upload, Distance Measurement, Florence-2 Model, Keypoint Visualization, Text Display, Dot Visualization, Llama 3.2 Vision, Roboflow Custom Metadata, PTZ Tracking (ONVIF).md), Dynamic Crop, Detections Merge, Mask Area Measurement

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>"
}