app.py

import gradio as gr
import cv2
import numpy as np
import torch
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForDepthEstimation

# Load depth estimation model
image_processor = AutoImageProcessor.from_pretrained("depth-anything/Depth-Anything-V2-Small-hf")
depth_model = AutoModelForDepthEstimation.from_pretrained("depth-anything/Depth-Anything-V2-Small-hf")

def apply_blur(image, blur_type, blur_strength, depth_threshold):
    # Convert image to RGB
    img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    
    # Depth estimation
    pil_image = Image.fromarray(img)
    inputs = image_processor(images=pil_image, return_tensors="pt")
    
    with torch.no_grad():
        outputs = depth_model(**inputs)
        predicted_depth = outputs.predicted_depth

    # Interpolate to original size
    prediction = torch.nn.functional.interpolate(
        predicted_depth.unsqueeze(1),
        size=img.shape[:2],
        mode="bicubic",
        align_corners=False,
    )

    # Create mask based on depth threshold
    mask = prediction[0, 0, :, :].detach().cpu().numpy() < depth_threshold
    mask = mask.astype(np.uint8)
    mask = np.repeat(mask[:, :, np.newaxis], 3, axis=2) * 255

    # Apply blur based on selected type
    if blur_type == "Gaussian":
        blurred_image = cv2.GaussianBlur(img, (0, 0), sigmaX=blur_strength)
    elif blur_type == "Lens":
        # Simulate lens blur using a larger kernel
        kernel_size = int(blur_strength * 2) * 2 + 1
        blurred_image = cv2.GaussianBlur(img, (kernel_size, kernel_size), 0)

    # Combine blurred and original images using the mask
    output = np.where(mask == 255, img, blurred_image)
    
    return output

# Define Gradio interface
iface = gr.Interface(
    fn=apply_blur,
    inputs=[
        gr.Image(label="Input Image"),
        gr.Radio(["Gaussian", "Lens"], label="Blur Type"),
        gr.Slider(1, 30, value=15, step=1, label="Blur Strength"),
        gr.Slider(1, 10, value=3, step=0.1, label="Depth Threshold")
    ],
    outputs=gr.Image(label="Output Image"),
    title="Image Segmentation and Blurring",
    description="Upload an image and apply Gaussian or Lens blur to the background based on depth estimation."
)

# Launch the app
iface.launch(share=True)