Update vtoonify/model/encoder/align_all_parallel.py

vtoonify/model/encoder/align_all_parallel.py

@@ -10,11 +10,17 @@ import insightface
 import multiprocessing as mp
 import math
 
-def get_landmark(image, face_detector):
-    """Get landmark with InsightFace
-    :return: np.array shape=(106, 2) for 106-point landmarks
+def get_landmark(filepath, face_detector):
+    """get landmark with InsightFace
+    :return: np.array shape=(68, 2)
     """
-    faces = face_detector.get(image)
+    if isinstance(filepath, str):
+        img = PIL.Image.open(filepath)
+        img = np.array(img)
+    else:
+        img = filepath
+
+    faces = face_detector.get(img)
     
     if len(faces) == 0:
         print('Error: no face detected!')
@@ -22,43 +28,89 @@ def get_landmark(image, face_detector):
     
     # Assume the first detected face is the target
     face = faces[0]
-    lm = face.landmark_2d_106
+    lm = face.landmark_2d_106[:, :2]  # Use 106-point landmarks
     return lm
 
-def align_face(image, face_detector):
+def align_face(filepath, face_detector):
     """
-    :param image: np.ndarray
+    :param filepath: str
     :return: PIL Image
     """
-    lm = get_landmark(image, face_detector)
+    lm = get_landmark(filepath, face_detector)
     if lm is None:
-        return None
-
-    # Calculate auxiliary vectors for alignment
-    eye_left = np.mean(lm[36:42], axis=0)
-    eye_right = np.mean(lm[42:48], axis=0)
-    mouth_left = lm[48]
-    mouth_right = lm[54]
+        return None    
+    
+    # Use the same landmark indices as before
+    lm_eye_left = lm[36: 42]  # left-clockwise
+    lm_eye_right = lm[42: 48]  # left-clockwise
+    lm_mouth_outer = lm[48: 60]  # left-clockwise
 
-    # Calculate transformation parameters
-    eye_center = (eye_left + eye_right) / 2
-    mouth_center = (mouth_left + mouth_right) / 2
+    # Calculate auxiliary vectors.
+    eye_left = np.mean(lm_eye_left, axis=0)
+    eye_right = np.mean(lm_eye_right, axis=0)
+    eye_avg = (eye_left + eye_right) * 0.5
     eye_to_eye = eye_right - eye_left
-    eye_to_mouth = mouth_center - eye_center
+    mouth_left = lm_mouth_outer[0]
+    mouth_right = lm_mouth_outer[6]
+    mouth_avg = (mouth_left + mouth_right) * 0.5
+    eye_to_mouth = mouth_avg - eye_avg
 
-    # Define the transformation matrix
+    # Choose oriented crop rectangle.
     x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
     x /= np.hypot(*x)
-    x *= np.hypot(*eye_to_eye) * 2.0
+    x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
     y = np.flipud(x) * [-1, 1]
-    c = eye_center + eye_to_mouth * 0.1
+    c = eye_avg + eye_to_mouth * 0.1
     quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
     qsize = np.hypot(*x) * 2
 
-    # Transform and crop the image
-    transform_size = 256
+    # read image
+    if isinstance(filepath, str):
+        img = PIL.Image.open(filepath)
+    else:
+        img = PIL.Image.fromarray(filepath)
+
     output_size = 256
-    img = PIL.Image.fromarray(image)
+    transform_size = 256
+    enable_padding = True
+
+    # Shrink.
+    shrink = int(np.floor(qsize / output_size * 0.5))
+    if shrink > 1:
+        rsize = (int(np.rint(float(img.size[0]) / shrink)), int(np.rint(float(img.size[1]) / shrink)))
+        img = img.resize(rsize, PIL.Image.ANTIALIAS)
+        quad /= shrink
+        qsize /= shrink
+
+    # Crop.
+    border = max(int(np.rint(qsize * 0.1)), 3)
+    crop = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
+            int(np.ceil(max(quad[:, 1]))))
+    crop = (max(crop[0] - border, 0), max(crop[1] - border, 0), min(crop[2] + border, img.size[0]),
+            min(crop[3] + border, img.size[1]))
+    if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
+        img = img.crop(crop)
+        quad -= crop[0:2]
+
+    # Pad.
+    pad = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
+           int(np.ceil(max(quad[:, 1]))))
+    pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0), max(pad[2] - img.size[0] + border, 0),
+           max(pad[3] - img.size[1] + border, 0))
+    if enable_padding and max(pad) > border - 4:
+        pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
+        img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
+        h, w, _ = img.shape
+        y, x, _ = np.ogrid[:h, :w, :1]
+        mask = np.maximum(1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w - 1 - x) / pad[2]),
+                          1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h - 1 - y) / pad[3]))
+        blur = qsize * 0.02
+        img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
+        img += (np.median(img, axis=(0, 1)) - img) * np.clip(mask, 0.0, 1.0)
+        img = PIL.Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
+        quad += pad[:2]
+
+    # Transform.
     img = img.transform((transform_size, transform_size), PIL.Image.QUAD, (quad + 0.5).flatten(), PIL.Image.BILINEAR)
     if output_size < transform_size:
         img = img.resize((output_size, output_size), PIL.Image.ANTIALIAS)
@@ -72,23 +124,19 @@ def chunks(lst, n):
 
 def extract_on_paths(file_paths, face_detector):
     pid = mp.current_process().name
-    print(f'\t{pid} is starting to extract on #{len(file_paths)} images')
+    print('\t{} is starting to extract on #{} images'.format(pid, len(file_paths)))
     tot_count = len(file_paths)
     count = 0
     for file_path, res_path in file_paths:
         count += 1
         if count % 100 == 0:
-            print(f'{pid} done with {count}/{tot_count}')
+            print('{} done with {}/{}'.format(pid, count, tot_count))
         try:
-            img = cv2.imread(file_path, cv2.IMREAD_COLOR)
-            img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
-            res = align_face(img_rgb, face_detector)
-            if res is not None:
-                res = res.convert('RGB')
-                os.makedirs(os.path.dirname(res_path), exist_ok=True)
-                res.save(res_path)
-        except Exception as e:
-            print(f"Error processing {file_path}: {e}")
+            res = align_face(file_path, face_detector)
+            res = res.convert('RGB')
+            os.makedirs(os.path.dirname(res_path), exist_ok=True)
+            res.save(res_path)
+        except Exception:
             continue
     print('\tDone!')
 
@@ -118,16 +166,16 @@ def run(args):
     file_chunks = list(chunks(file_paths, int(math.ceil(len(file_paths) / args.num_threads))))
     print(len(file_chunks))
     pool = mp.Pool(args.num_threads)
-    print(f'Running on {len(file_paths)} paths\nHere we goooo')
+    print('Running on {} paths\nHere we goooo'.format(len(file_paths)))
     tic = time.time()
     pool.starmap(extract_on_paths, [(chunk, face_detector) for chunk in file_chunks])
     toc = time.time()
-    print(f'Mischief managed in {toc - tic}s')
+    print('Mischief managed in {}s'.format(toc - tic))
 
 if __name__ == '__main__':
     # Initialize InsightFace
     face_detector = insightface.app.FaceAnalysis()
-    face_detector.prepare(ctx_id=-1, det_size=(640, 640))  # Use -1 for CPU
+    face_detector.prepare(ctx_id=-1, det_size=(640, 640))  # ctx_id=-1 for CPU
 
     args = parse_args()
     run(args)