Skip to content

Pixelate Visualization

Class: PixelateVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.pixelate.v1.PixelateVisualizationBlockV1

Apply a pixelated mosaic effect to detected objects, creating a blocky, pixelated appearance that obscures object details while maintaining recognizable shapes, useful for privacy protection and content anonymization.

How This Block Works

This block takes an image and detection predictions and applies a pixelation (mosaic) effect to the detected objects, leaving the background unchanged. The block:

  1. Takes an image and predictions as input
  2. Identifies detected regions from bounding boxes or segmentation masks
  3. Divides the detected object regions into square blocks (pixels) of the specified size
  4. Replaces each block with a single color value (typically the average color of that block), creating a mosaic-like pixelated effect
  5. Preserves the background and areas outside detected objects unchanged
  6. Returns an annotated image where detected objects are pixelated with blocky, mosaic appearance, while the rest of the image remains sharp

The block works with both object detection predictions (using bounding boxes) and instance segmentation predictions (using masks). When masks are available, it pixelates the exact shape of detected objects; otherwise, it pixelates rectangular bounding box regions. The pixel size parameter controls how large each square block is, where larger pixel sizes create more pronounced pixelation with fewer, larger blocks (more obscured), while smaller pixel sizes create finer pixelation with more, smaller blocks (less obscured). Unlike blur visualization (which creates smooth, gradient-like obscuration), pixelation creates distinct, blocky squares that maintain a more stylized, mosaic appearance while still effectively obscuring details.

Common Use Cases

  • Privacy Protection and Anonymization: Pixelate faces, people, license plates, or other sensitive information in images or videos to protect privacy, comply with data protection regulations, or anonymize content before sharing or publishing, using the distinctive pixelated mosaic effect
  • Content Filtering and Censorship: Obscure inappropriate or sensitive content in images or videos for content moderation workflows, safe content previews, or user-generated content filtering, where the pixelated effect provides clear visual indication that content has been processed
  • Stylized Content Anonymization: Create pixelated effects for artistic or stylized content anonymization where the mosaic appearance is preferred over smooth blur, useful for creative projects, stylized presentations, or distinctive visual effects
  • Visual Emphasis and Focus: Pixelate detected objects to draw attention to other parts of the image, create visual contrast between pixelated foreground objects and sharp backgrounds, or emphasize specific elements in composition with a distinctive visual style
  • Security and Surveillance: Anonymize people, vehicles, or other identifiable elements in security footage or surveillance images while preserving scene context, using pixelation as an alternative to blur for a more stylized anonymization effect
  • Documentation and Reporting: Create pixelated, anonymized versions of images for reports, documentation, or case studies where sensitive information needs to be obscured but overall context should remain visible, with a distinctive mosaic aesthetic

Connecting to Other Blocks

The annotated image from this block can be connected to:

  • Other visualization blocks (e.g., Label Visualization, Bounding Box Visualization, Polygon Visualization) to add additional annotations on top of pixelated objects for comprehensive visualization or to indicate what was pixelated
  • Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save pixelated images for documentation, reporting, or archiving privacy-protected content
  • Webhook blocks to send pixelated images to external systems, APIs, or web applications for content moderation, privacy-compliant sharing, or anonymized analysis
  • Notification blocks (e.g., Email Notification, Slack Notification) to send pixelated images as privacy-protected visual evidence in alerts or reports
  • Video output blocks to create annotated video streams or recordings with pixelated objects for live monitoring, privacy-compliant video processing, or post-processing analysis

Type identifier

Use the following identifier in step "type" field: roboflow_core/pixelate_visualization@v1to add the block as as step in your workflow.

Properties

Name Type Description Refs
name str Enter a unique identifier for this step.. ❌
copy_image bool Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations.. ✅
pixel_size int Size of each square pixel block in the pixelated effect, measured in pixels. Controls the granularity of the pixelation: larger values create bigger, more blocky pixels with stronger obscuration (fewer blocks, more abstract appearance), while smaller values create finer, more detailed pixelation (more blocks, less obscured). Typical values range from 10 to 50 pixels, with 20 being a good default that balances obscuration with recognizable object shape.. ✅

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 Pixelate Visualization in version v1.

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Pixelate Visualization in version v1 has.

Bindings

  • input

    • image (image): The image to visualize on..
    • copy_image (boolean): Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations..
    • predictions (Union[rle_instance_segmentation_prediction, object_detection_prediction, keypoint_detection_prediction, instance_segmentation_prediction]): Model predictions to visualize..
    • pixel_size (integer): Size of each square pixel block in the pixelated effect, measured in pixels. Controls the granularity of the pixelation: larger values create bigger, more blocky pixels with stronger obscuration (fewer blocks, more abstract appearance), while smaller values create finer, more detailed pixelation (more blocks, less obscured). Typical values range from 10 to 50 pixels, with 20 being a good default that balances obscuration with recognizable object shape..

  • output

    • image (image): Image in workflows.
Example JSON definition of step Pixelate Visualization in version v1 
{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/pixelate_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions": "$steps.object_detection_model.predictions",
    "pixel_size": 20
}