Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import numpy as np | |
| import torch | |
| from PIL import Image | |
| import cv2 | |
| import requests | |
| from transformers import pipeline | |
| # Load the depth estimation pipeline | |
| pipe = pipeline(task="depth-estimation", model="depth-anything/Depth-Anything-V2-Small-hf") | |
| def apply_depth_aware_blur_inverse( | |
| image, | |
| foreground_blur, | |
| midground_blur, | |
| background_blur, | |
| foreground_threshold, | |
| midground_lower, | |
| midground_upper, | |
| background_threshold, | |
| ): | |
| original_image = Image.fromarray(image).convert("RGB") | |
| original_image = original_image.resize((512, 512)) | |
| image_np = np.array(original_image) | |
| # Inference | |
| depth = pipe(original_image)["depth"] | |
| depth = np.array(depth) # Convert to numpy array | |
| depth = cv2.resize(depth, (512, 512), interpolation=cv2.INTER_CUBIC) # Resize depth map | |
| # Normalize the depth map | |
| normalized_depth_map = (depth - np.min(depth)) / (np.max(depth) - np.min(depth)) | |
| # Create masks (Inverted Logic) | |
| foreground_mask = (normalized_depth_map >= foreground_threshold).astype(np.uint8) * 255 | |
| midground_mask = ((normalized_depth_map < foreground_threshold) & (normalized_depth_map >= background_threshold)).astype(np.uint8) * 255 | |
| background_mask = (normalized_depth_map < background_threshold).astype(np.uint8) * 255 | |
| blurred_image = np.copy(np.array(original_image)) | |
| # Apply blur, ensuring kernel size is valid (Inverted Blur) | |
| if foreground_blur > 0 and foreground_blur % 2 == 1: | |
| blurred_image = np.where( | |
| (foreground_mask[..., None] == 255), | |
| cv2.GaussianBlur(blurred_image, (foreground_blur, foreground_blur), 10), | |
| blurred_image, | |
| ) | |
| if midground_blur > 0 and midground_blur % 2 == 1: | |
| blurred_image = np.where( | |
| (midground_mask[..., None] == 255), | |
| cv2.GaussianBlur(blurred_image, (midground_blur, midground_blur), 8), | |
| blurred_image, | |
| ) | |
| if background_blur > 0 and background_blur % 2 == 1: | |
| blurred_image = np.where( | |
| (background_mask[..., None] == 255), | |
| cv2.GaussianBlur(blurred_image, (background_blur, background_blur), 20), | |
| blurred_image, | |
| ) | |
| return Image.fromarray(blurred_image.astype(np.uint8)) | |
| # Example input values (including defaults) | |
| example_image = np.zeros((512, 512, 3), dtype=np.uint8) # Placeholder for an image | |
| example_inputs = [ | |
| example_image, | |
| 35, # foreground_blur | |
| 7, # midground_blur | |
| 15, # background_blur (default) | |
| 0.6, # foreground_threshold (default) | |
| 0.6, # midground_lower (default) | |
| 0.2, # midground_upper (default) | |
| 0.2, # background_threshold (default) | |
| ] | |
| iface = gr.Interface( | |
| fn=apply_depth_aware_blur_inverse, # Changed function name | |
| inputs=[ | |
| gr.Image(label="Input Image"), | |
| gr.Slider(1, 51, step=2, label="Foreground Blur Kernel Size"), | |
| gr.Slider(1, 51, step=2, label="Midground Blur Kernel Size"), | |
| gr.Slider(1, 51, step=2, label="Background Blur Kernel Size"), | |
| gr.Slider(0, 1, label="Foreground Threshold"), | |
| gr.Slider(0, 1, label="Midground Lower Threshold"), | |
| gr.Slider(0, 1, label="Midground Upper Threshold"), | |
| gr.Slider(0, 1, label="Background Threshold"), | |
| ], | |
| outputs=gr.Image(label="Blurred Image"), | |
| title="Inverse Depth-Aware Lens Blur App", # Changed title | |
| description="Apply inverse depth-based blur to uploaded images using Depth Anything V2. Closer objects are blurred, farther objects are sharper.", # Changed description | |
| examples=[example_inputs], # Provide example inputs | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() |