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