Update vtoonify/model/encoder/align_all_parallel.py

vtoonify/model/encoder/align_all_parallel.py

@@ -10,17 +10,11 @@ import insightface
 import multiprocessing as mp
 import math
 
-def get_landmark(filepath, face_detector):
-    """get landmark with InsightFace
-    :return: np.array shape=(68, 2)
+def get_landmark(image, face_detector):
+    """Get landmark with InsightFace
+    :return: np.array shape=(106, 2) for 106-point landmarks
     """
-    if isinstance(filepath, str):
-        img = PIL.Image.open(filepath)
-        img = np.array(img)
-    else:
-        img = filepath
-
-    faces = face_detector.get(img)
+    faces = face_detector.get(image)
     
     if len(faces) == 0:
         print('Error: no face detected!')
@@ -28,89 +22,43 @@ def get_landmark(filepath, face_detector):
     
     # Assume the first detected face is the target
     face = faces[0]
-    lm = face.landmark_2d_106[:, :2]  # Use 106-point landmarks
+    lm = face.landmark_2d_106
     return lm
 
-def align_face(filepath, face_detector):
+def align_face(image, face_detector):
     """
-    :param filepath: str
+    :param image: np.ndarray
     :return: PIL Image
     """
-    lm = get_landmark(filepath, face_detector)
+    lm = get_landmark(image, face_detector)
     if lm is None:
-        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
+        return None
 
-    # 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
+    # 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]
+
+    # Calculate transformation parameters
+    eye_center = (eye_left + eye_right) / 2
+    mouth_center = (mouth_left + mouth_right) / 2
     eye_to_eye = eye_right - eye_left
-    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
+    eye_to_mouth = mouth_center - eye_center
 
-    # Choose oriented crop rectangle.
+    # Define the transformation matrix
     x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
     x /= np.hypot(*x)
-    x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
+    x *= np.hypot(*eye_to_eye) * 2.0
     y = np.flipud(x) * [-1, 1]
-    c = eye_avg + eye_to_mouth * 0.1
+    c = eye_center + 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
 
-    # read image
-    if isinstance(filepath, str):
-        img = PIL.Image.open(filepath)
-    else:
-        img = PIL.Image.fromarray(filepath)
-
-    output_size = 256
+    # Transform and crop the 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.
+    output_size = 256
+    img = PIL.Image.fromarray(image)
     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)
@@ -124,19 +72,23 @@ def chunks(lst, n):
 
 def extract_on_paths(file_paths, face_detector):
     pid = mp.current_process().name
-    print('\t{} is starting to extract on #{} images'.format(pid, len(file_paths)))
+    print(f'\t{pid} is starting to extract on #{len(file_paths)} images')
     tot_count = len(file_paths)
     count = 0
     for file_path, res_path in file_paths:
         count += 1
         if count % 100 == 0:
-            print('{} done with {}/{}'.format(pid, count, tot_count))
+            print(f'{pid} done with {count}/{tot_count}')
         try:
-            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:
+            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}")
             continue
     print('\tDone!')
 
@@ -166,16 +118,16 @@ 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('Running on {} paths\nHere we goooo'.format(len(file_paths)))
+    print(f'Running on {len(file_paths)} paths\nHere we goooo')
     tic = time.time()
     pool.starmap(extract_on_paths, [(chunk, face_detector) for chunk in file_chunks])
     toc = time.time()
-    print('Mischief managed in {}s'.format(toc - tic))
+    print(f'Mischief managed in {toc - tic}s')
 
 if __name__ == '__main__':
     # Initialize InsightFace
     face_detector = insightface.app.FaceAnalysis()
-    face_detector.prepare(ctx_id=-1, det_size=(640, 640))  # ctx_id=-1 for CPU
+    face_detector.prepare(ctx_id=-1, det_size=(640, 640))  # Use -1 for CPU
 
     args = parse_args()
     run(args)