README.md

metadata

title: Image Blur Effects
emoji: 🖼️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.23.1
app_file: app.py
pinned: false

Image Blur Effects using Segmentation and Depth Estimation

This Hugging Face Space demonstrates how to apply two different blur effects to images:

1. Gaussian Background Blur: Uses image segmentation to identify the foreground object and apply a Gaussian blur to the background
2. Depth-Based Lens Blur: Uses monocular depth estimation to create a realistic lens blur effect, with blur intensity proportional to estimated depth

How to Use

1. Upload an image with a clear foreground subject
2. Choose a blur effect type
3. Adjust the blur strength
4. For Gaussian Background Blur, specify the target class (e.g., person, cat, dog)
5. Click "Apply Effect"

Models Used

• Image Segmentation: facebook/maskformer-swin-base-ade
• Depth Estimation: intel/dpt-large