Update utils_mask.py

utils_mask.py

@@ -62,51 +62,61 @@ def get_mask_location(model_type, category, model_parse: Image.Image, keypoint:
     else:
         raise ValueError("model_type must be 'hd' or 'dc'!")
 
-    parse_head = (parse_array == 1).astype(np.float32) + \
-                 (parse_array == 3).astype(np.float32) + \
-                 (parse_array == 11).astype(np.float32)
+    parse_head = (parse_array == label_map["hat"]).astype(np.float32) + \
+                 (parse_array == label_map["hair"]).astype(np.float32) + \
+                 (parse_array == label_map["head"]).astype(np.float32)
 
     parser_mask_fixed = (parse_array == label_map["left_shoe"]).astype(np.float32) + \
                         (parse_array == label_map["right_shoe"]).astype(np.float32) + \
-                        (parse_array == label_map["hat"]).astype(np.float32) + \
                         (parse_array == label_map["sunglasses"]).astype(np.float32) + \
-                        (parse_array == label_map["bag"]).astype(np.float32)
+                        (parse_array == label_map["bag"]).astype(np.float32) + \
+                        (parse_array == label_map["scarf"]).astype(np.float32)
 
     parser_mask_changeable = (parse_array == label_map["background"]).astype(np.float32)
 
-    arms_left = (parse_array == 14).astype(np.float32)
-    arms_right = (parse_array == 15).astype(np.float32)
+    arms_left = (parse_array == label_map["left_arm"]).astype(np.float32)
+    arms_right = (parse_array == label_map["right_arm"]).astype(np.float32)
 
     if category == 'dresses':
-        # Initial dress mask for the upper body
+        # Combine upper body category logic
         parse_mask_upper = (parse_array == 4).astype(np.float32) + (parse_array == 7).astype(np.float32)
-        
-        # Create a mask for the legs (including skirts and pants)
-        parse_mask_legs = np.logical_or.reduce((parse_array == label_map["skirt"],
-                                                parse_array == label_map["pants"],
-                                                parse_array == label_map["left_leg"],
-                                                parse_array == label_map["right_leg"])).astype(np.float32)
-        
-        # Dilate the leg mask to ensure coverage and fill gaps
+        parser_mask_fixed_lower_cloth = (parse_array == label_map["skirt"]).astype(np.float32) + \
+                                        (parse_array == label_map["pants"]).astype(np.float32)
+        parser_mask_fixed += parser_mask_fixed_lower_cloth
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+
+        # Combine lower body category logic
+        parse_mask_legs = (parse_array == 6).astype(np.float32) + \
+                          (parse_array == 12).astype(np.float32) + \
+                          (parse_array == 13).astype(np.float32) + \
+                          (parse_array == 5).astype(np.float32)
+        parser_mask_fixed += (parse_array == label_map["upper_clothes"]).astype(np.float32) + \
+                             (parse_array == label_map["left_arm"]).astype(np.float32) + \
+                             (parse_array == label_map["right_arm"]).astype(np.float32)
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+
+        # Fill gaps between legs
         parse_mask_legs = cv2.dilate(parse_mask_legs.astype(np.uint8), np.ones((6, 6), np.uint8), iterations=6)
-        
+
         # Combine the upper body mask with the leg mask
         parse_mask = np.maximum(parse_mask_upper, parse_mask_legs)
 
-
     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) + \
                                         (parse_array == label_map["pants"]).astype(np.float32)
         parser_mask_fixed += parser_mask_fixed_lower_cloth
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+
     elif category == 'lower_body':
         parse_mask = (parse_array == 6).astype(np.float32) + \
                      (parse_array == 12).astype(np.float32) + \
                      (parse_array == 13).astype(np.float32) + \
                      (parse_array == 5).astype(np.float32)
         parser_mask_fixed += (parse_array == label_map["upper_clothes"]).astype(np.float32) + \
-                             (parse_array == 14).astype(np.float32) + \
-                             (parse_array == 15).astype(np.float32)
+                             (parse_array == label_map["left_arm"]).astype(np.float32) + \
+                             (parse_array == label_map["right_arm"]).astype(np.float32)
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
     else:
         raise NotImplementedError
 
@@ -130,7 +140,7 @@ def get_mask_location(model_type, category, model_parse: Image.Image, keypoint:
         size_left = [shoulder_left[0] - ARM_LINE_WIDTH // 2, shoulder_left[1] - ARM_LINE_WIDTH // 2, shoulder_left[0] + ARM_LINE_WIDTH // 2, shoulder_left[1] + ARM_LINE_WIDTH // 2]
         size_right = [shoulder_right[0] - ARM_LINE_WIDTH // 2, shoulder_right[1] - ARM_LINE_WIDTH // 2, shoulder_right[0] + ARM_LINE_WIDTH // 2,
                       shoulder_right[1] + ARM_LINE_WIDTH // 2]
-        
+
         if wrist_right[0] <= 1. and wrist_right[1] <= 1.:
             im_arms_right = arms_right
         else:
@@ -150,10 +160,10 @@ def get_mask_location(model_type, category, model_parse: Image.Image, keypoint:
         parser_mask_fixed += hands_left + hands_right
 
     parser_mask_fixed = np.logical_or(parser_mask_fixed, parse_head)
-    parse_mask = cv2.dilate(parse_mask.astype(np.uint8), np.ones((5, 5), np.uint8), iterations=5)
+    parse_mask = cv2.dilate(parse_mask, np.ones((5, 5), np.uint8), iterations=5)
     if category == 'dresses' or category == 'upper_body':
         neck_mask = (parse_array == 18).astype(np.float32)
-        neck_mask = cv2.dilate(neck_mask.astype(np.uint8), np.ones((5, 5), np.uint8), iterations=1)
+        neck_mask = cv2.dilate(neck_mask, np.ones((5, 5), np.uint8), iterations=1)
         neck_mask = np.logical_and(neck_mask, np.logical_not(parse_head))
         parse_mask = np.logical_or(parse_mask, neck_mask)
         arm_mask = cv2.dilate(np.logical_or(im_arms_left, im_arms_right).astype('float32'), np.ones((5, 5), np.uint8), iterations=4)