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

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>"
}