File size: 5,099 Bytes
47b2ea7 0e3fe1f 47b2ea7 0e3fe1f cafcff1 0e3fe1f 47b2ea7 a8db7a5 cafcff1 a8db7a5 0e3fe1f a8db7a5 0e3fe1f a8db7a5 0e3fe1f a8db7a5 47b2ea7 0e3fe1f 47b2ea7 0e3fe1f 47b2ea7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
import insightface
import numpy as np
from PIL import Image, ImageOps
import cv2
from scipy.ndimage import gaussian_filter
# Load InsightFace models
try:
detector = insightface.model_zoo.get_model('retinaface_mnet025_v2')
detector.prepare(ctx_id=-1) # Use CPU, set ctx_id=0 for GPU
except Exception as e:
print(f"Error loading face detection model: {e}")
detector = None
try:
landmark_model = insightface.model_zoo.get_model('2d106det')
landmark_model.prepare(ctx_id=-1) # Use CPU, set ctx_id=0 for GPU
except Exception as e:
print(f"Error loading landmark model: {e}")
landmark_model = None
def align(image_in, face_index=0, output_size=256):
if detector is None or landmark_model is None:
print("Models not loaded properly.")
return image_in, 0, None
try:
image_in = ImageOps.exif_transpose(image_in)
except:
print("Exif problem, not rotating")
landmarks = list(get_landmarks(image_in))
n_faces = len(landmarks)
face_index = min(n_faces-1, face_index)
if n_faces == 0:
aligned_image = image_in
quad = None
else:
aligned_image, quad = image_align(image_in, landmarks[face_index], output_size=output_size)
return aligned_image, n_faces, quad
def get_landmarks(image):
"""Get landmarks from PIL image"""
if detector is None or landmark_model is None:
return []
img = np.array(image)
bboxes, _ = detector.detect(img, threshold=0.5, scale=1.0)
for bbox in bboxes:
# Use the landmark model to predict landmarks
landmarks = landmark_model.get(img, bbox)
yield landmarks
def image_align(src_img, face_landmarks, output_size=512, transform_size=2048, enable_padding=True, x_scale=1, y_scale=1, em_scale=0.1, alpha=False):
# Align function modified from ffhq-dataset
# See https://github.com/NVlabs/ffhq-dataset for license
lm = np.array(face_landmarks)
lm_eye_left = lm[2:3] # left-clockwise
lm_eye_right = lm[0:1] # left-clockwise
# 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 = 0.71 * (eye_right - eye_left)
mouth_avg = lm[4]
eye_to_mouth = 1.35 * (mouth_avg - eye_avg)
# Choose oriented crop rectangle.
x = eye_to_eye.copy()
x /= np.hypot(*x)
x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
x *= x_scale
y = np.flipud(x) * [-y_scale, y_scale]
c = eye_avg + eye_to_mouth * em_scale
quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
quad_orig = quad.copy()
qsize = np.hypot(*x) * 2
img = src_img.convert('RGBA').convert('RGB')
# 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, Image.Resampling.LANCZOS)
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 += (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 = np.uint8(np.clip(np.rint(img), 0, 255))
if alpha:
mask = 1 - np.clip(3.0 * mask, 0.0, 1.0)
mask = np.uint8(np.clip(np.rint(mask * 255), 0, 255))
img = np.concatenate((img, mask), axis=2)
img = Image.fromarray(img, 'RGBA')
else:
img = Image.fromarray(img, 'RGB')
quad += pad[:2]
# Transform.
img = img.transform((transform_size, transform_size), Image.QUAD, (quad + 0.5).flatten(), Image.BILINEAR)
if output_size < transform_size:
img = img.resize((output_size, output_size), Image.Resampling.LANCZOS)
return img, quad_orig |