Update utils_mask.py

utils_mask.py

@@ -24,11 +24,11 @@ label_map = {
 }
 
 def extend_arm_mask(wrist, elbow, scale):
-    wrist = elbow + scale * (wrist - elbow)
-    return wrist
+  wrist = elbow + scale * (wrist - elbow)
+  return wrist
 
 def hole_fill(img):
-    img = np.pad(img[1:-1, 1:-1], pad_width=1, mode='constant', constant_values=0)
+    img = np.pad(img[1:-1, 1:-1], pad_width = 1, mode = 'constant', constant_values=0)
     img_copy = img.copy()
     mask = np.zeros((img.shape[0] + 2, img.shape[1] + 2), dtype=np.uint8)
 
@@ -51,7 +51,7 @@ def refine_mask(mask):
 
     return refine_mask
 
-def get_mask_location(model_type, category, model_parse: Image.Image, keypoint: dict, width=384, height=512):
+def get_mask_location(model_type, category, model_parse: Image.Image, keypoint: dict, width=384,height=512):
     im_parse = model_parse.resize((width, height), Image.NEAREST)
     parse_array = np.array(im_parse)
 
@@ -60,58 +60,48 @@ def get_mask_location(model_type, category, model_parse: Image.Image, keypoint:
     elif model_type == 'dc':
         arm_width = 45
     else:
-        raise ValueError("model_type must be 'hd' or 'dc'!")
+        raise ValueError("model_type must be \'hd\' or \'dc\'!")
 
-    parse_head = (parse_array == label_map["head"]).astype(np.float32) + \
-                 (parse_array == label_map["hat"]).astype(np.float32) + \
-                 (parse_array == label_map["hair"]).astype(np.float32) + \
-                 (parse_array == label_map["sunglasses"]).astype(np.float32)
+    parse_head = (parse_array == 1).astype(np.float32) + \
+                 (parse_array == 3).astype(np.float32) + \
+                 (parse_array == 11).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["bag"]).astype(np.float32) + \
-                        (parse_array == label_map["scarf"]).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)
 
     parser_mask_changeable = (parse_array == label_map["background"]).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 (excluding head)
-        parse_mask_upper = np.logical_or((parse_array == label_map["upper_clothes"]), (parse_array == label_map["dress"])).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)
+    arms_left = (parse_array == 14).astype(np.float32)
+    arms_right = (parse_array == 15).astype(np.float32)
 
-        # Dilate the leg mask to ensure coverage and fill gaps
-        parse_mask_legs_dilated = cv2.dilate(parse_mask_legs.astype(np.uint8), np.ones((6, 6), np.uint8), iterations=6)
+    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)
 
-        # Combine the upper body mask with the dilated leg mask
-        parse_mask = np.maximum(parse_mask_upper, parse_mask_legs_dilated)
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
 
     elif category == 'upper_body':
-        parse_mask = (parse_array == label_map["upper_clothes"]).astype(np.float32)
-
+        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 == label_map["pants"]).astype(np.float32) + \
-                     (parse_array == label_map["skirt"]).astype(np.float32) + \
-                     (parse_array == label_map["left_leg"]).astype(np.float32) + \
-                     (parse_array == label_map["right_leg"]).astype(np.float32)
-
+        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 == label_map["left_arm"]).astype(np.float32) + \
-                             (parse_array == label_map["right_arm"]).astype(np.float32)
-
+                             (parse_array == 14).astype(np.float32) + \
+                             (parse_array == 15).astype(np.float32)
         parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
-
     else:
-        raise NotImplementedError("Category not implemented")
+        raise NotImplementedError
 
     # Load pose points
     pose_data = keypoint["pose_keypoints_2d"]
@@ -122,7 +112,6 @@ def get_mask_location(model_type, category, model_parse: Image.Image, keypoint:
     im_arms_right = Image.new('L', (width, height))
     arms_draw_left = ImageDraw.Draw(im_arms_left)
     arms_draw_right = ImageDraw.Draw(im_arms_right)
-
     if category == 'dresses' or category == 'upper_body':
         shoulder_right = np.multiply(tuple(pose_data[2][:2]), height / 512.0)
         shoulder_left = np.multiply(tuple(pose_data[5][:2]), height / 512.0)
@@ -134,6 +123,7 @@ 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
@@ -154,9 +144,7 @@ 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.uint16), iterations=5)
     if category == 'dresses' or category == 'upper_body':
         neck_mask = (parse_array == 18).astype(np.float32)
         neck_mask = cv2.dilate(neck_mask, np.ones((5, 5), np.uint16), iterations=1)
@@ -176,4 +164,4 @@ def get_mask_location(model_type, category, model_parse: Image.Image, keypoint:
     mask = Image.fromarray(inpaint_mask.astype(np.uint8) * 255)
     mask_gray = Image.fromarray(inpaint_mask.astype(np.uint8) * 127)
 
-    return mask, mask_gray
+    return mask, mask_gray