forked from ashawkey/torch-ngp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
llff2nerf.py
131 lines (104 loc) · 4.02 KB
/
llff2nerf.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
from audioop import avg
import os
import glob
import numpy as np
import math
import json
import argparse
# returns point closest to both rays of form o+t*d, and a weight factor that goes to 0 if the lines are parallel
def closest_point_2_lines(oa, da, ob, db):
da = da / np.linalg.norm(da)
db = db / np.linalg.norm(db)
c = np.cross(da, db)
denom = np.linalg.norm(c)**2
t = ob - oa
ta = np.linalg.det([t, db, c]) / (denom + 1e-10)
tb = np.linalg.det([t, da, c]) / (denom + 1e-10)
if ta > 0:
ta = 0
if tb > 0:
tb = 0
return (oa+ta*da+ob+tb*db) * 0.5, denom
def rotmat(a, b):
a, b = a / np.linalg.norm(a), b / np.linalg.norm(b)
v = np.cross(a, b)
c = np.dot(a, b)
s = np.linalg.norm(v)
kmat = np.array([[0, -v[2], v[1]], [v[2], 0, -v[0]], [-v[1], v[0], 0]])
return np.eye(3) + kmat + kmat.dot(kmat) * ((1 - c) / (s ** 2 + 1e-10))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('path', type=str, help="root directory to the LLFF dataset (contains images/ and pose_bounds.npy)")
parser.add_argument('--images', type=str, default='images', help="images folder")
parser.add_argument('--downscale', type=float, default=1, help="image size down scale")
opt = parser.parse_args()
print(f'[INFO] process {opt.path}')
# load data
images = [f[len(opt.path):] for f in sorted(glob.glob(os.path.join(opt.path, opt.images, "*"))) if f.lower().endswith('png') or f.lower().endswith('jpg') or f.lower().endswith('jpeg')]
poses_bounds = np.load(os.path.join(opt.path, 'poses_bounds.npy'))
N = poses_bounds.shape[0]
print(f'[INFO] loaded {len(images)} images, {N} poses_bounds as {poses_bounds.shape}')
assert N == len(images)
poses = poses_bounds[:, :15].reshape(-1, 3, 5) # (N, 3, 5)
bounds = poses_bounds[:, -2:] # (N, 2)
H, W, fl = poses[0, :, -1]
H = H // opt.downscale
W = W // opt.downscale
fl = fl / opt.downscale
print(f'[INFO] H = {H}, W = {W}, fl = {fl} (downscale = {opt.downscale})')
# inversion of this: https://github.com/Fyusion/LLFF/blob/c6e27b1ee59cb18f054ccb0f87a90214dbe70482/llff/poses/pose_utils.py#L51
poses = np.concatenate([poses[..., 1:2], poses[..., 0:1], -poses[..., 2:3], poses[..., 3:4]], -1) # (N, 3, 4)
# to homogeneous
last_row = np.tile(np.array([0, 0, 0, 1]), (len(poses), 1, 1)) # (N, 1, 4)
poses = np.concatenate([poses, last_row], axis=1) # (N, 4, 4)
# the following stuff are from colmap2nerf...
poses[:, 0:3, 1] *= -1
poses[:, 0:3, 2] *= -1
poses = poses[:, [1, 0, 2, 3], :] # swap y and z
poses[:, 2, :] *= -1 # flip whole world upside down
up = poses[:, 0:3, 1].sum(0)
up = up / np.linalg.norm(up)
R = rotmat(up, [0, 0, 1]) # rotate up vector to [0,0,1]
R = np.pad(R, [0, 1])
R[-1, -1] = 1
poses = R @ poses
totw = 0.0
totp = np.array([0.0, 0.0, 0.0])
for i in range(N):
mf = poses[i, :3, :]
for j in range(i + 1, N):
mg = poses[j, :3, :]
p, w = closest_point_2_lines(mf[:,3], mf[:,2], mg[:,3], mg[:,2])
#print(i, j, p, w)
if w > 0.01:
totp += p * w
totw += w
totp /= totw
print(f'[INFO] totp = {totp}')
poses[:, :3, 3] -= totp
avglen = np.linalg.norm(poses[:, :3, 3], axis=-1).mean()
poses[:, :3, 3] *= 4.0 / avglen
print(f'[INFO] average radius = {avglen}')
# construct frames
frames = []
for i in range(N):
frames.append({
'file_path': images[i],
'transform_matrix': poses[i].tolist(),
})
# construct a transforms.json
transforms = {
'w': W,
'h': H,
'fl_x': fl,
'fl_y': fl,
'cx': W // 2,
'cy': H // 2,
'aabb_scale': 2,
'frames': frames,
}
# write
output_path = os.path.join(opt.path, 'transforms.json')
print(f'[INFO] write to {output_path}')
with open(output_path, 'w') as f:
json.dump(transforms, f, indent=2)