app.py

import gradio as gr
from PIL import Image, ImageFilter, ImageOps
import numpy as np
import torch
from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation, DPTFeatureExtractor, DPTForDepthEstimation
import cv2

# Load segmentation model
seg_model_name = "nvidia/segformer-b1-finetuned-ade-512-512"
seg_feature_extractor = SegformerFeatureExtractor.from_pretrained(seg_model_name)
seg_model = SegformerForSemanticSegmentation.from_pretrained(seg_model_name)

# Load depth estimation model
depth_model_name = "Intel/dpt-hybrid-midas"
depth_feature_extractor = DPTFeatureExtractor.from_pretrained(depth_model_name)
depth_model = DPTForDepthEstimation.from_pretrained(depth_model_name)

# Device configuration
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
seg_model.to(device)
depth_model.to(device)

def process_image(image):
    # Ensure image is in RGB format and resize
    image = ImageOps.exif_transpose(image).resize((512, 512))

    # Perform segmentation
    inputs = seg_feature_extractor(images=image, return_tensors="pt").to(device)
    with torch.no_grad():
        outputs = seg_model(**inputs)
        logits = outputs.logits
        segmentation = torch.argmax(logits, dim=1)[0].cpu().numpy()
    binary_mask = np.where(segmentation > 0, 255, 0).astype(np.uint8)

    # Apply Gaussian Blur to the background
    blurred_background = image.filter(ImageFilter.GaussianBlur(15))
    foreground = Image.fromarray(binary_mask).convert("L").resize(image.size)
    output_blur = Image.composite(image, blurred_background, foreground)

    # Depth estimation for lens blur
    depth_inputs = depth_feature_extractor(images=image, return_tensors="pt").to(device)
    with torch.no_grad():
        depth_outputs = depth_model(**depth_inputs)
        predicted_depth = depth_outputs.predicted_depth.squeeze().cpu().numpy()

    # Normalize depth map
    depth_min, depth_max = predicted_depth.min(), predicted_depth.max()
    normalized_depth = (predicted_depth - depth_min) / (depth_max - depth_min)
    normalized_depth_resized = cv2.resize(normalized_depth, (512, 512))

    # Lens blur using depth map
    blurred_image = np.array(image).astype(np.float32)
    blur_intensity = normalized_depth_resized * 20
    for y in range(image.size[1]):
        for x in range(image.size[0]):
            sigma = blur_intensity[y, x]
            kernel_size = int(2 * sigma + 1)
            if kernel_size > 1:
                patch = image.crop((x - kernel_size//2, y - kernel_size//2, x + kernel_size//2 + 1, y + kernel_size//2 + 1))
                patch = patch.filter(ImageFilter.GaussianBlur(sigma))
                blurred_image[y, x, :] = np.array(patch)[kernel_size//2, kernel_size//2, :]
    lens_blur_image = Image.fromarray(np.clip(blurred_image, 0, 255).astype(np.uint8))

    return image, output_blur, lens_blur_image

iface = gr.Interface(
    fn=process_image,
    inputs=gr.Image(type="pil", label="Upload an Image"),
    outputs=[
        gr.Image(label="Original Image"),
        gr.Image(label="Gaussian Blur Effect"),
        gr.Image(label="Depth-Based Lens Blur Effect")
    ],
    title="Image Blurring with Gaussian and Depth-Based Lens Blur",
    description="Upload an image to see Gaussian blur and depth-based lens blur effects."
)

iface.launch()