File size: 3,306 Bytes
560350a 899326c 560350a d602acc 560350a 91cc172 560350a 91cc172 560350a 899326c 560350a 899326c 1b245f3 560350a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
import gradio as gr
import numpy as np
import torch
from PIL import Image, ImageFilter
from transformers import pipeline, SegformerFeatureExtractor, SegformerForSemanticSegmentation
# Load the pre-trained segmentation model
feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b1-finetuned-cityscapes-1024-1024")
segmentation_model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b1-finetuned-cityscapes-1024-1024")
def apply_blur_effect(image, blur_type):
"""
Applies either Gaussian blur to the whole image,
depth-based blur, or background blur while keeping the foreground sharp.
"""
image = image.resize((512, 512)) # Resize input image
if blur_type == "Depth-Based Blur(Lens Blur)":
# Use depth estimation model to get depth map
depth_estimator = pipeline(task="depth-estimation", model="Intel/zoedepth-nyu-kitti")
outputs = depth_estimator(image)
depth_map = np.array(outputs["depth"])
# Normalize depth map
depth_map_normalized = (depth_map - np.min(depth_map)) / (np.max(depth_map) - np.min(depth_map))
depth_array = np.clip(depth_map_normalized * 5, 0, 5).astype(int) # Scale depth to select blur levels
# Generate different levels of Gaussian blur
blur_levels = [image.filter(ImageFilter.GaussianBlur(radius=r)) for r in range(6)]
# Create depth-based blur image
depth_based_blur_image = Image.new("RGB", image.size)
for i in range(image.width):
for j in range(image.height):
blur_level = depth_array[j, i]
depth_based_blur_image.putpixel((i, j), blur_levels[blur_level].getpixel((i, j)))
return depth_based_blur_image
elif blur_type == "Gaussian Background Blur":
# Perform segmentation to get foreground and background masks
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = segmentation_model(**inputs)
logits = outputs.logits # Shape: (batch, num_classes, height, width)
predicted_mask = torch.argmax(logits, dim=1).squeeze().cpu().numpy()
# Create a binary mask (1 = foreground, 0 = background)
foreground_mask = (predicted_mask == 11).astype(np.uint8)
# Convert the mask into a PIL image for processing
mask_image = Image.fromarray((foreground_mask * 255).astype(np.uint8)).resize(image.size)
# Apply Gaussian blur to the entire image
blurred_image = image.filter(ImageFilter.GaussianBlur(radius=15))
# Blend the sharp foreground and blurred background
final_image = Image.composite(image, blurred_image, mask_image)
return final_image
return image
# Gradio UI
interface = gr.Interface(
fn=apply_blur_effect,
inputs=[
gr.Image(type="pil"),
gr.Radio(["Depth-Based Blur(Lens Blur)", "Gaussian Background Blur"], label="Blur Type"),
],
outputs="image",
title="Image Blur Effects: Gaussian Background Blur, Depth-Based Blur(Lens Blur)",
description="Upload a selfie (needs some background, not just the face!) and apply Gaussian Background Blur or Depth-Based Blur(Lens Blur)",
)
# Launch the Gradio app
if __name__ == "__main__":
interface.launch()
|