Update app.py

app.py

@@ -455,60 +455,9 @@ def depth_to_mesh(depth_map, image, resolution=100, detail_level='medium'):
     mesh.fix_normals()
     
     return mesh
-
-    # Enhanced image preprocessing to properly handle PNGs with transparency
-def preprocess_image(image_path):
-    with Image.open(image_path) as img:
-        # Get original mode to check if it has transparency
-        original_mode = img.mode
+       
+       
         
-        # Convert to RGB or RGBA as needed
-        if original_mode == 'RGBA':
-            # Keep alpha channel for transparency
-            img = img.convert("RGBA")
-        else:
-            # Otherwise use RGB
-            img = img.convert("RGB")
-        
-        # Resize if the image is too large
-        if img.width > MAX_DIMENSION or img.height > MAX_DIMENSION:
-            # Calculate new dimensions while preserving aspect ratio
-            if img.width > img.height:
-                new_width = MAX_DIMENSION
-                new_height = int(img.height * (MAX_DIMENSION / img.width))
-            else:
-                new_height = MAX_DIMENSION
-                new_width = int(img.width * (MAX_DIMENSION / img.height))
-            
-            # Use high-quality Lanczos resampling for better detail preservation
-            img = img.resize((new_width, new_height), Image.LANCZOS)
-        
-        # Handle enhancement only for RGB (non-transparent) parts
-        if original_mode != 'RGBA':
-            # Convert to numpy array for additional preprocessing
-            img_array = np.array(img)
-            
-            # Optional: Apply adaptive histogram equalization for better contrast
-            # This helps the depth model detect more details
-            if len(img_array.shape) == 3 and img_array.shape[2] == 3:
-                # Convert to LAB color space
-                lab = cv2.cvtColor(img_array, cv2.COLOR_RGB2LAB)
-                l, a, b = cv2.split(lab)
-                
-                # Apply CLAHE to L channel
-                clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
-                cl = clahe.apply(l)
-                
-                # Merge channels back
-                enhanced_lab = cv2.merge((cl, a, b))
-                
-                # Convert back to RGB
-                img_array = cv2.cvtColor(enhanced_lab, cv2.COLOR_LAB2RGB)
-                
-                # Convert back to PIL Image
-                img = Image.fromarray(img_array)
-        
-        return img
 
 @app.route('/health', methods=['GET'])
 def health_check():