File size: 3,124 Bytes
e9be89f |
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 79 80 81 82 83 84 85 86 87 88 |
import gradio as gr
import cv2
import numpy as np
import torch
from PIL import Image
from transformers import (
SegformerImageProcessor,
SegformerForSemanticSegmentation,
AutoImageProcessor,
AutoModelForDepthEstimation
)
# Load Segformer model for Gaussian blur
segformer_processor = SegformerImageProcessor.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
segformer_model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
# Load Depth-Anything model for lens blur
depth_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 = image
if blur_type == "Gaussian":
# Use Segformer for Gaussian blur
pil_image = Image.fromarray(img)
inputs = segformer_processor(images=pil_image, return_tensors="pt")
outputs = segformer_model(**inputs)
logits = outputs.logits
mask = logits[0, 12, :, :].detach().cpu().numpy() > depth_threshold
mask = cv2.resize(mask.astype(np.uint8), (img.shape[1], img.shape[0]))
elif blur_type == "Lens":
# Use Depth-Anything for lens blur
pil_image = Image.fromarray(img)
inputs = depth_processor(images=pil_image, return_tensors="pt")
with torch.no_grad():
outputs = depth_model(**inputs)
predicted_depth = outputs.predicted_depth
prediction = torch.nn.functional.interpolate(
predicted_depth.unsqueeze(1),
size=img.shape[:2],
mode="bicubic",
align_corners=False,
)
mask = prediction[0, 0, :, :].detach().cpu().numpy() > depth_threshold
mask = mask.astype(np.uint8)
# Invert mask using cv2
mask = cv2.bitwise_not(mask)
mask = np.repeat(mask[:, :, np.newaxis], 3, axis=2)
# 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, blurred_image, img)
return output
# Define Gradio interface
iface = gr.Interface(
fn=apply_blur,
inputs=[
gr.Image(label="Input Image"),
gr.Radio(["Gaussian", "Lens"], label="Blur Type", value="Gaussian"),
gr.Slider(1, 30, value=15, step=1, label="Blur Strength"),
gr.Slider(-20, 20, value=-4, 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 using different segmentation models."
)
# Launch the app
iface.launch(share=True)
|