Pixelator: A Pixelation-based Deidentification Operator

Authors: NVIDIA Holoscan Team (NVIDIA)
Supported platforms: x86_64, aarch64
Language: Python
Last modified: May 13, 2025
Latest version: 1.0
Minimum Holoscan SDK version: 3.0.0
Tested Holoscan SDK versions: 3.1.0
Contribution metric: Level 1 - Highly Reliable

This directory contains the PixelatorOp for use with NVIDIA Holoscan workflows. The operator performs pixelation-based deidentification on input images, suitable for applications such as surgical video anonymization.

Structure

• pixelator.py: The main operator implementation (class PixelatorOp).
• README.md: This file.
• metadata.json: Operator metadata.

Requirements

• Holoscan SDK
• cupy

Example Usage

from holohub.operators.deidentification.pixelator import PixelatorOp
op = PixelatorOp(block_size_h=16, block_size_w=16)

Parameters

• block_size_h: Height of the pixelation block.
• block_size_w: Width of the pixelation block.