Update utils_mask.py

utils_mask.py

@@ -79,22 +79,26 @@ def get_mask_location(model_type, category, model_parse: Image.Image, keypoint:
 
     if category == 'dresses':
         parse_mask = (parse_array == 7).astype(np.float32) + \
-                     (parse_array == 4).astype(np.float32) + \
-                     (parse_array == 5).astype(np.float32) + \
-                     (parse_array == 6).astype(np.float32)
+                    (parse_array == 4).astype(np.float32) + \
+                    (parse_array == 5).astype(np.float32) + \
+                    (parse_array == 6).astype(np.float32)
 
         parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
-        
-        # Create a separate mask for the gap between legs
-        leg_gap_mask = (parse_array == 12).astype(np.float32) + \
-                    (parse_array == 13).astype(np.float32)
+
+        # Create a separate mask for the leg parts
+        leg_mask = (parse_array == 12).astype(np.float32) + \
+                (parse_array == 13).astype(np.float32)
 
         # Fill gaps between legs
-        leg_gap_filled = cv2.dilate(leg_gap_mask.astype(np.uint8), np.ones((10, 10), np.uint8), iterations=10)
+        leg_gap_filled = cv2.dilate(leg_mask.astype(np.uint8), np.ones((10, 10), np.uint8), iterations=10)
 
-        # Add the gap-filled mask to the existing parse_mask
+        # Ensure the filled leg gaps do not affect the upper body
+        leg_gap_filled = np.logical_and(leg_gap_filled, leg_mask).astype(np.float32)
+
+        # Add the filled leg gaps to the parse_mask
         parse_mask += leg_gap_filled
 
+
     elif category == 'upper_body':
         parse_mask = (parse_array == 4).astype(np.float32) + (parse_array == 7).astype(np.float32)
         parser_mask_fixed_lower_cloth = (parse_array == label_map["skirt"]).astype(np.float32) + \