Slider changes

app.py

@@ -57,7 +57,6 @@ def segmentation_blur_effect(input_image: Image.Image):
     
     # Convert predicted mask to a PIL image and ensure it matches imageResized's size
     pred_pil = transforms.ToPILImage()(pred)
-    # Resize mask to match imageResized to avoid size mismatch in OpenCV operations
     mask = pred_pil.resize(imageResized.size)
     
     # Convert mask to grayscale and threshold to create a binary mask
@@ -84,14 +83,24 @@ def segmentation_blur_effect(input_image: Image.Image):
     return finalImg_pil, mask
 
 # -----------------------------
-# Define the Depth-Based Lens Blur Effect
+# Define the Depth-Based Lens Blur Effect with Slider-Controlled Thresholds
 # -----------------------------
-def lens_blur_effect(input_image: Image.Image):
+def lens_blur_effect(input_image: Image.Image, fg_threshold: float = 85, mg_threshold: float = 170):
     """
     Uses DepthPro to estimate a depth map and applies a dynamic lens blur effect
-    by blending three versions of the image (foreground, middleground, background)
-    with increasing blur levels. Returns the depth map, the final lens-blurred image,
-    and the depth masks.
+    by blending three versions of the image with increasing blur levels.
+    
+    Parameters:
+      input_image: The original PIL image.
+      fg_threshold: Foreground threshold (0-255). Pixels with depth below this are considered foreground.
+      mg_threshold: Middleground threshold (0-255). Pixels with depth between fg_threshold and mg_threshold are middleground.
+    
+    Returns:
+      depthImg: The computed depth map (PIL Image).
+      lensBlurImage: The final lens-blurred image (PIL Image).
+      mask_fg_img: Foreground depth mask.
+      mask_mg_img: Middleground depth mask.
+      mask_bg_img: Background depth mask.
     """
     # Process the image with the depth estimation model
     inputs = depth_processor(images=input_image, return_tensors="pt").to(device)
@@ -117,9 +126,9 @@ def lens_blur_effect(input_image: Image.Image):
     img_middleground = cv2.GaussianBlur(img, (0, 0), sigmaX=7, sigmaY=7)
     img_background = cv2.GaussianBlur(img, (0, 0), sigmaX=15, sigmaY=15)
     
-    # Define depth thresholds (using 1/3 and 2/3 of 255)
-    threshold1 = 255 / 3      # ~85
-    threshold2 = 2 * 255 / 3  # ~170
+    # Use slider values as thresholds
+    threshold1 = fg_threshold   # e.g., default 85
+    threshold2 = mg_threshold   # e.g., default 170
     
     # Create masks for foreground, middleground, and background based on depth
     mask_fg = (depth_map < threshold1).astype(np.float32)
@@ -131,7 +140,7 @@ def lens_blur_effect(input_image: Image.Image):
     mask_mg_3 = np.stack([mask_mg]*3, axis=-1)
     mask_bg_3 = np.stack([mask_bg]*3, axis=-1)
     
-    # Blend the images using the masks (vectorized operation)
+    # Blend the images using the masks
     final_img = (img_foreground * mask_fg_3 +
                  img_middleground * mask_mg_3 +
                  img_background * mask_bg_3).astype(np.uint8)
@@ -149,17 +158,21 @@ def lens_blur_effect(input_image: Image.Image):
 # -----------------------------
 # Gradio App: Process Image and Display Multiple Effects
 # -----------------------------
-def process_image(input_image: Image.Image):
+def process_image(input_image: Image.Image, fg_threshold: float, mg_threshold: float):
     """
     Processes the uploaded image to generate:
       1. Segmentation-based Gaussian blur effect.
       2. Segmentation mask.
       3. Depth map.
       4. Depth-based lens blur effect.
-      5. Depth-based masks for foreground, middleground, and background.
+      5. Depth masks for foreground, middleground, and background.
+    
+    The depth thresholds for foreground and middleground regions are adjustable via sliders.
     """
     seg_blur, seg_mask = segmentation_blur_effect(input_image)
-    depth_map_img, lens_blur_img, mask_fg_img, mask_mg_img, mask_bg_img = lens_blur_effect(input_image)
+    depth_map_img, lens_blur_img, mask_fg_img, mask_mg_img, mask_bg_img = lens_blur_effect(
+        input_image, fg_threshold, mg_threshold
+    )
     
     return (
         seg_blur,
@@ -171,17 +184,21 @@ def process_image(input_image: Image.Image):
         mask_bg_img
     )
 
-title = "Blur Effects: Gaussian Blur & Depth-Based Lens Blur"
+title = "Blur Effects: Gaussian & Depth-Based Lens Blur with Adjustable Depth Thresholds"
 description = (
     "Upload an image to apply two distinct effects:\n\n"
     "1. A segmentation-based Gaussian blur that blurs the background (using RMBG-2.0).\n"
     "2. A depth-based lens blur effect that simulates realistic lens blur based on depth (using DepthPro).\n\n"
-    "Outputs include the blurred image, segmentation mask, depth map, lens-blurred image, and individual depth masks."
+    "Use the sliders to adjust the foreground and middleground depth thresholds."
 )
 
 demo = gr.Interface(
     fn=process_image,
-    inputs=gr.Image(type="pil", label="Input Image"),
+    inputs=[
+        gr.Image(type="pil", label="Input Image"),
+        gr.Slider(minimum=0, maximum=255, step=1, value=85, label="Foreground Depth Threshold"),
+        gr.Slider(minimum=0, maximum=255, step=1, value=170, label="Middleground Depth Threshold")
+    ],
     outputs=[
         gr.Image(type="pil", label="Segmentation-Based Blur"),
         gr.Image(type="pil", label="Segmentation Mask"),