File size: 7,448 Bytes
2f99bb4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 |
from imutils import face_utils
import numpy as np
import random
import albumentations as alb
from .DeepFakeMask import dfl_full, extended, components, facehull
import cv2
def IoUfrom2bboxes(boxA, boxB):
xA = max(boxA[0], boxB[0])
yA = max(boxA[1], boxB[1])
xB = min(boxA[2], boxB[2])
yB = min(boxA[3], boxB[3])
interArea = max(0, xB - xA + 1) * max(0, yB - yA + 1)
boxAArea = (boxA[2] - boxA[0] + 1) * (boxA[3] - boxA[1] + 1)
boxBArea = (boxB[2] - boxB[0] + 1) * (boxB[3] - boxB[1] + 1)
iou = interArea / float(boxAArea + boxBArea - interArea)
return iou
def reorder_landmark(landmark):
landmark_add = np.zeros((13, 2))
for idx, idx_l in enumerate([77, 75, 76, 68, 69, 70, 71, 80, 72, 73, 79, 74, 78]):
landmark_add[idx] = landmark[idx_l]
landmark[68:] = landmark_add
return landmark
def get_dlib_landmarks(inp, dlib_face_detector, dlib_face_predictor):
faces = dlib_face_detector(inp, 1)
if len(faces)==0:
raise Exception("No faces detected")
landmarks=[]
size_list=[]
for face_idx in range(len(faces)):
landmark = dlib_face_predictor(inp, faces[face_idx])
landmark = face_utils.shape_to_np(landmark)
x0,y0=landmark[:,0].min(),landmark[:,1].min()
x1,y1=landmark[:,0].max(),landmark[:,1].max()
face_s=(x1-x0)*(y1-y0)
size_list.append(face_s)
landmarks.append(landmark)
landmarks=np.concatenate(landmarks).reshape((len(size_list),)+landmark.shape)
landmarks=landmarks[np.argsort(np.array(size_list))[::-1]]
return landmarks
def get_retina_bbox(inp,face_detector):
faces = face_detector.predict_jsons(inp)
landmarks=[]
size_list=[]
for face_idx in range(len(faces)):
x0,y0,x1,y1=faces[face_idx]['bbox']
landmark=np.array([[x0,y0],[x1,y1]]+faces[face_idx]['landmarks'])
face_s=(x1-x0)*(y1-y0)
size_list.append(face_s)
landmarks.append(landmark)
landmarks=np.concatenate(landmarks).reshape((len(size_list),)+landmark.shape)
landmarks=landmarks[np.argsort(np.array(size_list))[::-1]]
return landmarks
def random_get_hull(landmark,img, face_region):
face_region = int(face_region)
if face_region == 1:
mask = dfl_full(landmarks=landmark.astype('int32'),face=img, channels=3).mask
elif face_region == 2:
mask = extended(landmarks=landmark.astype('int32'),face=img, channels=3).mask
elif face_region == 3:
mask = components(landmarks=landmark.astype('int32'),face=img, channels=3).mask
else:
mask = facehull(landmarks=landmark.astype('int32'),face=img, channels=3).mask
return mask/255
class RandomDownScale(alb.core.transforms_interface.ImageOnlyTransform):
def apply(self,img,**params):
return self.randomdownscale(img)
def randomdownscale(self,img):
keep_ratio=True
keep_input_shape=True
H,W,C=img.shape
ratio_list=[2,4]
r=ratio_list[np.random.randint(len(ratio_list))]
img_ds=cv2.resize(img,(int(W/r),int(H/r)),interpolation=cv2.INTER_NEAREST)
if keep_input_shape:
img_ds=cv2.resize(img_ds,(W,H),interpolation=cv2.INTER_LINEAR)
return img_ds
def get_source_transforms():
return alb.Compose([
alb.Compose([
alb.RGBShift((-20, 20), (-20, 20), (-20, 20), p=0.3),
alb.HueSaturationValue(
hue_shift_limit=(-0.3, 0.3), sat_shift_limit=(-0.3, 0.3), val_shift_limit=(-0.3, 0.3), p=1),
alb.RandomBrightnessContrast(
brightness_limit=(-0.1, 0.1), contrast_limit=(-0.1, 0.1), p=1),
], p=1),
alb.OneOf([
RandomDownScale(p=1),
alb.Sharpen(alpha=(0.2, 0.5), lightness=(0.5, 1.0), p=1),
], p=1),
], p=1.)
def randaffine(img, mask):
f = alb.Affine(
translate_percent={'x': (-0.03, 0.03), 'y': (-0.015, 0.015)},
scale=[0.95, 1/0.95],
fit_output=False,
p=1)
g = alb.ElasticTransform(
alpha=50,
sigma=7,
alpha_affine=0,
p=1,
)
transformed = f(image=img, mask=mask)
img = transformed['image']
mask = transformed['mask']
transformed = g(image=img, mask=mask)
mask = transformed['mask']
return img, mask
def get_blend_mask(mask):
H,W=mask.shape
size_h=np.random.randint(192,257)
size_w=np.random.randint(192,257)
mask=cv2.resize(mask,(size_w,size_h))
kernel_1=random.randrange(5,26,2)
kernel_1=(kernel_1,kernel_1)
kernel_2=random.randrange(5,26,2)
kernel_2=(kernel_2,kernel_2)
mask_blured = cv2.GaussianBlur(mask, kernel_1, 0)
mask_blured = mask_blured/(mask_blured.max())
mask_blured[mask_blured<1]=0
mask_blured = cv2.GaussianBlur(mask_blured, kernel_2, np.random.randint(5,46))
mask_blured = mask_blured/(mask_blured.max())
mask_blured = cv2.resize(mask_blured,(W,H))
return mask_blured.reshape((mask_blured.shape+(1,)))
def dynamic_blend(source,target,mask,blending_type, mixup_ratio=[0.25,0.5,0.75,1,1,1]):
"""Performs dynamic blending of source and target, using the mask as the blending region
Args:
source: source image
target: target image
mask: mask image
Returns:
img_blended: blended image
mask_blurred: augmented mask used for blending
"""
mask_blured = get_blend_mask(mask)
mask_blured_copy = mask_blured.copy()
if blending_type == "Poisson":
# Poisson blending
b_mask = (mask_blured_copy * 255).astype(np.uint8)
l, t, w, h = cv2.boundingRect(b_mask)
center = (int(l + w / 2), int(t + h / 2))
img_blended = cv2.seamlessClone(source, target, b_mask, center, cv2.NORMAL_CLONE)
else:
# Mix up blending
blend_list=mixup_ratio
blend_ratio = blend_list[np.random.randint(len(blend_list))]
mask_blured_copy = mask_blured.copy()
mask_blured_copy*=blend_ratio
img_blended=(mask_blured_copy * source + (1 - mask_blured_copy) * target)
return img_blended,mask_blured
def get_transforms():
return alb.Compose([
alb.RGBShift((-20, 20), (-20, 20), (-20, 20), p=0.3),
alb.HueSaturationValue(
hue_shift_limit=(-0.3, 0.3), sat_shift_limit=(-0.3, 0.3), val_shift_limit=(-0.3, 0.3), p=0.3),
alb.RandomBrightnessContrast(
brightness_limit=(-0.3, 0.3), contrast_limit=(-0.3, 0.3), p=0.3),
alb.ImageCompression(quality_lower=40, quality_upper=100, p=0.5),
],
additional_targets={f'image1': 'image'},
p=1.)
def self_blending(img, landmark, blending_type, face_region):
if np.random.rand() < 0.25:
landmark = landmark[:68]
mask = random_get_hull(landmark, img, face_region)
if mask.shape[-1] == 3:
mask = mask[:, :, 0]
mask_copy = mask
source_transforms = get_source_transforms()
source = img.copy()
source = source_transforms(image=source.astype(np.uint8))['image']
source_before_affine_transforms, mask_before_affine_transforms = source, mask
source, mask = randaffine(source, mask)
source_after_affine_transforms, mask_after_affine_transforms = source, mask
img_blended, mask = dynamic_blend(source, img, mask, blending_type)
img_blended = img_blended.astype(np.uint8)
img = img.astype(np.uint8)
return img, img_blended, mask, mask_copy, source_before_affine_transforms, mask_before_affine_transforms, source_after_affine_transforms, mask_after_affine_transforms |