-
Notifications
You must be signed in to change notification settings - Fork 245
/
pose_utils.py
285 lines (215 loc) · 9.43 KB
/
pose_utils.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
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
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
import numpy as np
import os
import sys
import imageio
import skimage.transform
from llff.poses.colmap_wrapper import run_colmap
import llff.poses.colmap_read_model as read_model
def load_colmap_data(realdir):
camerasfile = os.path.join(realdir, 'sparse/0/cameras.bin')
camdata = read_model.read_cameras_binary(camerasfile)
# cam = camdata[camdata.keys()[0]]
list_of_keys = list(camdata.keys())
cam = camdata[list_of_keys[0]]
print( 'Cameras', len(cam))
h, w, f = cam.height, cam.width, cam.params[0]
# w, h, f = factor * w, factor * h, factor * f
hwf = np.array([h,w,f]).reshape([3,1])
imagesfile = os.path.join(realdir, 'sparse/0/images.bin')
imdata = read_model.read_images_binary(imagesfile)
w2c_mats = []
bottom = np.array([0,0,0,1.]).reshape([1,4])
names = [imdata[k].name for k in imdata]
print( 'Images #', len(names))
perm = np.argsort(names)
for k in imdata:
im = imdata[k]
R = im.qvec2rotmat()
t = im.tvec.reshape([3,1])
m = np.concatenate([np.concatenate([R, t], 1), bottom], 0)
w2c_mats.append(m)
w2c_mats = np.stack(w2c_mats, 0)
c2w_mats = np.linalg.inv(w2c_mats)
poses = c2w_mats[:, :3, :4].transpose([1,2,0])
poses = np.concatenate([poses, np.tile(hwf[..., np.newaxis], [1,1,poses.shape[-1]])], 1)
points3dfile = os.path.join(realdir, 'sparse/0/points3D.bin')
pts3d = read_model.read_points3d_binary(points3dfile)
# must switch to [-u, r, -t] from [r, -u, t], NOT [r, u, -t]
poses = np.concatenate([poses[:, 1:2, :], poses[:, 0:1, :], -poses[:, 2:3, :], poses[:, 3:4, :], poses[:, 4:5, :]], 1)
return poses, pts3d, perm
def save_poses(basedir, poses, pts3d, perm):
pts_arr = []
vis_arr = []
for k in pts3d:
pts_arr.append(pts3d[k].xyz)
cams = [0] * poses.shape[-1]
for ind in pts3d[k].image_ids:
if len(cams) < ind - 1:
print('ERROR: the correct camera poses for current points cannot be accessed')
return
cams[ind-1] = 1
vis_arr.append(cams)
pts_arr = np.array(pts_arr)
vis_arr = np.array(vis_arr)
print( 'Points', pts_arr.shape, 'Visibility', vis_arr.shape )
zvals = np.sum(-(pts_arr[:, np.newaxis, :].transpose([2,0,1]) - poses[:3, 3:4, :]) * poses[:3, 2:3, :], 0)
valid_z = zvals[vis_arr==1]
print( 'Depth stats', valid_z.min(), valid_z.max(), valid_z.mean() )
save_arr = []
for i in perm:
vis = vis_arr[:, i]
zs = zvals[:, i]
zs = zs[vis==1]
close_depth, inf_depth = np.percentile(zs, .1), np.percentile(zs, 99.9)
# print( i, close_depth, inf_depth )
save_arr.append(np.concatenate([poses[..., i].ravel(), np.array([close_depth, inf_depth])], 0))
save_arr = np.array(save_arr)
np.save(os.path.join(basedir, 'poses_bounds.npy'), save_arr)
def minify_v0(basedir, factors=[], resolutions=[]):
needtoload = False
for r in factors:
imgdir = os.path.join(basedir, 'images_{}'.format(r))
if not os.path.exists(imgdir):
needtoload = True
for r in resolutions:
imgdir = os.path.join(basedir, 'images_{}x{}'.format(r[1], r[0]))
if not os.path.exists(imgdir):
needtoload = True
if not needtoload:
return
def downsample(imgs, f):
sh = list(imgs.shape)
sh = sh[:-3] + [sh[-3]//f, f, sh[-2]//f, f, sh[-1]]
imgs = np.reshape(imgs, sh)
imgs = np.mean(imgs, (-2, -4))
return imgs
imgdir = os.path.join(basedir, 'images')
imgs = [os.path.join(imgdir, f) for f in sorted(os.listdir(imgdir))]
imgs = [f for f in imgs if any([f.endswith(ex) for ex in ['JPG', 'jpg', 'png', 'jpeg', 'PNG']])]
imgs = np.stack([imageio.imread(img)/255. for img in imgs], 0)
for r in factors + resolutions:
if isinstance(r, int):
name = 'images_{}'.format(r)
else:
name = 'images_{}x{}'.format(r[1], r[0])
imgdir = os.path.join(basedir, name)
if os.path.exists(imgdir):
continue
print('Minifying', r, basedir)
if isinstance(r, int):
imgs_down = downsample(imgs, r)
else:
imgs_down = skimage.transform.resize(imgs, [imgs.shape[0], r[0], r[1], imgs.shape[-1]],
order=1, mode='constant', cval=0, clip=True, preserve_range=False,
anti_aliasing=True, anti_aliasing_sigma=None)
os.makedirs(imgdir)
for i in range(imgs_down.shape[0]):
imageio.imwrite(os.path.join(imgdir, 'image{:03d}.png'.format(i)), (255*imgs_down[i]).astype(np.uint8))
def minify(basedir, factors=[], resolutions=[]):
needtoload = False
for r in factors:
imgdir = os.path.join(basedir, 'images_{}'.format(r))
if not os.path.exists(imgdir):
needtoload = True
for r in resolutions:
imgdir = os.path.join(basedir, 'images_{}x{}'.format(r[1], r[0]))
if not os.path.exists(imgdir):
needtoload = True
if not needtoload:
return
from shutil import copy
from subprocess import check_output
imgdir = os.path.join(basedir, 'images')
imgs = [os.path.join(imgdir, f) for f in sorted(os.listdir(imgdir))]
imgs = [f for f in imgs if any([f.endswith(ex) for ex in ['JPG', 'jpg', 'png', 'jpeg', 'PNG']])]
imgdir_orig = imgdir
wd = os.getcwd()
for r in factors + resolutions:
if isinstance(r, int):
name = 'images_{}'.format(r)
resizearg = '{}%'.format(int(100./r))
else:
name = 'images_{}x{}'.format(r[1], r[0])
resizearg = '{}x{}'.format(r[1], r[0])
imgdir = os.path.join(basedir, name)
if os.path.exists(imgdir):
continue
print('Minifying', r, basedir)
os.makedirs(imgdir)
check_output('cp {}/* {}'.format(imgdir_orig, imgdir), shell=True)
ext = imgs[0].split('.')[-1]
args = ' '.join(['mogrify', '-resize', resizearg, '-format', 'png', '*.{}'.format(ext)])
print(args)
os.chdir(imgdir)
check_output(args, shell=True)
os.chdir(wd)
if ext != 'png':
check_output('rm {}/*.{}'.format(imgdir, ext), shell=True)
print('Removed duplicates')
print('Done')
def load_data(basedir, factor=None, width=None, height=None, load_imgs=True):
poses_arr = np.load(os.path.join(basedir, 'poses_bounds.npy'))
poses = poses_arr[:, :-2].reshape([-1, 3, 5]).transpose([1,2,0])
bds = poses_arr[:, -2:].transpose([1,0])
img0 = [os.path.join(basedir, 'images', f) for f in sorted(os.listdir(os.path.join(basedir, 'images'))) \
if f.endswith('JPG') or f.endswith('jpg') or f.endswith('png')][0]
sh = imageio.imread(img0).shape
sfx = ''
if factor is not None:
sfx = '_{}'.format(factor)
minify(basedir, factors=[factor])
factor = factor
elif height is not None:
factor = sh[0] / float(height)
width = int(sh[1] / factor)
minify(basedir, resolutions=[[height, width]])
sfx = '_{}x{}'.format(width, height)
elif width is not None:
factor = sh[1] / float(width)
height = int(sh[0] / factor)
minify(basedir, resolutions=[[height, width]])
sfx = '_{}x{}'.format(width, height)
else:
factor = 1
imgdir = os.path.join(basedir, 'images' + sfx)
if not os.path.exists(imgdir):
print( imgdir, 'does not exist, returning' )
return
imgfiles = [os.path.join(imgdir, f) for f in sorted(os.listdir(imgdir)) if f.endswith('JPG') or f.endswith('jpg') or f.endswith('png')]
if poses.shape[-1] != len(imgfiles):
print( 'Mismatch between imgs {} and poses {} !!!!'.format(len(imgfiles), poses.shape[-1]) )
return
sh = imageio.imread(imgfiles[0]).shape
poses[:2, 4, :] = np.array(sh[:2]).reshape([2, 1])
poses[2, 4, :] = poses[2, 4, :] * 1./factor
if not load_imgs:
return poses, bds
# imgs = [imageio.imread(f, ignoregamma=True)[...,:3]/255. for f in imgfiles]
def imread(f):
if f.endswith('png'):
return imageio.imread(f, ignoregamma=True)
else:
return imageio.imread(f)
imgs = imgs = [imread(f)[...,:3]/255. for f in imgfiles]
imgs = np.stack(imgs, -1)
print('Loaded image data', imgs.shape, poses[:,-1,0])
return poses, bds, imgs
def gen_poses(basedir, match_type, factors=None):
files_needed = ['{}.bin'.format(f) for f in ['cameras', 'images', 'points3D']]
if os.path.exists(os.path.join(basedir, 'sparse/0')):
files_had = os.listdir(os.path.join(basedir, 'sparse/0'))
else:
files_had = []
if not all([f in files_had for f in files_needed]):
print( 'Need to run COLMAP' )
run_colmap(basedir, match_type)
else:
print('Don\'t need to run COLMAP')
print( 'Post-colmap')
poses, pts3d, perm = load_colmap_data(basedir)
save_poses(basedir, poses, pts3d, perm)
if factors is not None:
print( 'Factors:', factors)
minify(basedir, factors)
print( 'Done with imgs2poses' )
return True