forked from williamyang1991/DualStyleGAN
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathalign_caricature_data.py
125 lines (110 loc) · 5.44 KB
/
align_caricature_data.py
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
import numpy as np
import scipy.ndimage
import os
import PIL.Image
txtpath = './caricature.txt'
lmpath = './WebCaricature/FacialPoints/'
impath = './WebCaricature/OriginalImages/'
outpath = './Caricature/'
def image_align(src_file, dst_file, face_landmarks, output_size=1024, transform_size=4096, enable_padding=True, x_scale=1, y_scale=1, em_scale=0.1, alpha=False):
# Align function from FFHQ dataset pre-processing step
# https://github.com/NVlabs/ffhq-dataset/blob/master/download_ffhq.py
lm = np.array(face_landmarks)
'''
lm_chin = lm[0 : 17] # left-right
lm_eyebrow_left = lm[17 : 22] # left-right
lm_eyebrow_right = lm[22 : 27] # left-right
lm_nose = lm[27 : 31] # top-down
lm_nostrils = lm[31 : 36] # top-down
lm_eye_left = lm[36 : 42] # left-clockwise
lm_eye_right = lm[42 : 48] # left-clockwise
lm_mouth_outer = lm[48 : 60] # left-clockwise
lm_mouth_inner = lm[60 : 68] # left-clockwise
'''
lm_eye_left = lm[8:10]
lm_eye_right = lm[10:12]
lm_mouth_outer = lm[13:17]
# 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
'''
mouth_left = lm_mouth_outer[0]
mouth_right = lm_mouth_outer[6]
'''
mouth_left = lm_mouth_outer[1]
mouth_right = lm_mouth_outer[3]
mouth_avg = (mouth_left + mouth_right) * 0.5
eye_to_mouth = mouth_avg - eye_avg
# Choose oriented crop rectangle.
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 *= 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])
qsize = np.hypot(*x) * 2
# Load in-the-wild image.
if not os.path.isfile(src_file):
print('\nCannot find source image. Please run "--wilds" before "--align".')
return
img = PIL.Image.open(src_file).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, PIL.Image.ANTIALIAS)
quad /= shrink
qsize /= shrink
# Crop.
#border = max(int(np.rint(qsize * 0.7)), 1)
border = max(int(np.rint(qsize * 0.01)), 0.5)
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 - 2:
pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
#pad = np.maximum(pad, int(np.rint(qsize * 0.05)))
img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'edge')
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]))
#initial was *0.2
blur = qsize * 0.002
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 = 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 = PIL.Image.fromarray(img, 'RGBA')
else:
img = PIL.Image.fromarray(img, '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)
# Save aligned image.
img.save(dst_file, 'PNG')
if __name__ == "__main__":
if not os.path.exists(outpath):
os.makedirs(outpath)
f = open(txtpath,'r')
names = f.readlines()
f.close()
for name in names:
fname = name[:-8]
num = name[-7:-1]
lm = np.loadtxt(os.path.join(lmpath, fname.replace('_', ' '), num + '.txt'))
imgname = os.path.join(impath, fname.replace('_', ' '), num + '.jpg')
savename = os.path.join(outpath, fname + '_' + num + '.jpg')
image_align(imgname, savename, lm, output_size=256, transform_size=1024)