Spaces:
Running
Running
File size: 5,654 Bytes
9223079 4c88343 9223079 4c88343 9223079 4c88343 9223079 4c88343 9223079 4c88343 9223079 |
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 |
import argparse
import logging
import sqlite3
from collections import defaultdict
from pathlib import Path
import numpy as np
from tqdm import tqdm
from ...colmap_from_nvm import (
camera_center_to_translation,
recover_database_images_and_ids,
)
from ...utils.read_write_model import (
CAMERA_MODEL_IDS,
Camera,
Image,
Point3D,
write_model,
)
logger = logging.getLogger(__name__)
def read_nvm_model(nvm_path, database_path, image_ids, camera_ids, skip_points=False):
# Extract the intrinsics from the db file instead of the NVM model
db = sqlite3.connect(str(database_path))
ret = db.execute("SELECT camera_id, model, width, height, params FROM cameras;")
cameras = {}
for camera_id, camera_model, width, height, params in ret:
params = np.fromstring(params, dtype=np.double).reshape(-1)
camera_model = CAMERA_MODEL_IDS[camera_model]
assert len(params) == camera_model.num_params, (
len(params),
camera_model.num_params,
)
camera = Camera(
id=camera_id,
model=camera_model.model_name,
width=int(width),
height=int(height),
params=params,
)
cameras[camera_id] = camera
nvm_f = open(nvm_path, "r")
line = nvm_f.readline()
while line == "\n" or line.startswith("NVM_V3"):
line = nvm_f.readline()
num_images = int(line)
# assert num_images == len(cameras), (num_images, len(cameras))
logger.info(f"Reading {num_images} images...")
image_idx_to_db_image_id = []
image_data = []
i = 0
while i < num_images:
line = nvm_f.readline()
if line == "\n":
continue
data = line.strip("\n").lstrip("./").split(" ")
image_data.append(data)
image_idx_to_db_image_id.append(image_ids[data[0]])
i += 1
line = nvm_f.readline()
while line == "\n":
line = nvm_f.readline()
num_points = int(line)
if skip_points:
logger.info(f"Skipping {num_points} points.")
num_points = 0
else:
logger.info(f"Reading {num_points} points...")
points3D = {}
image_idx_to_keypoints = defaultdict(list)
i = 0
pbar = tqdm(total=num_points, unit="pts")
while i < num_points:
line = nvm_f.readline()
if line == "\n":
continue
data = line.strip("\n").split(" ")
x, y, z, r, g, b, num_observations = data[:7]
obs_image_ids, point2D_idxs = [], []
for j in range(int(num_observations)):
s = 7 + 4 * j
img_index, kp_index, kx, ky = data[s : s + 4]
image_idx_to_keypoints[int(img_index)].append(
(int(kp_index), float(kx), float(ky), i)
)
db_image_id = image_idx_to_db_image_id[int(img_index)]
obs_image_ids.append(db_image_id)
point2D_idxs.append(kp_index)
point = Point3D(
id=i,
xyz=np.array([x, y, z], float),
rgb=np.array([r, g, b], int),
error=1.0, # fake
image_ids=np.array(obs_image_ids, int),
point2D_idxs=np.array(point2D_idxs, int),
)
points3D[i] = point
i += 1
pbar.update(1)
pbar.close()
logger.info("Parsing image data...")
images = {}
for i, data in enumerate(image_data):
# Skip the focal length. Skip the distortion and terminal 0.
name, _, qw, qx, qy, qz, cx, cy, cz, _, _ = data
qvec = np.array([qw, qx, qy, qz], float)
c = np.array([cx, cy, cz], float)
t = camera_center_to_translation(c, qvec)
if i in image_idx_to_keypoints:
# NVM only stores triangulated 2D keypoints: add dummy ones
keypoints = image_idx_to_keypoints[i]
point2D_idxs = np.array([d[0] for d in keypoints])
tri_xys = np.array([[x, y] for _, x, y, _ in keypoints])
tri_ids = np.array([i for _, _, _, i in keypoints])
num_2Dpoints = max(point2D_idxs) + 1
xys = np.zeros((num_2Dpoints, 2), float)
point3D_ids = np.full(num_2Dpoints, -1, int)
xys[point2D_idxs] = tri_xys
point3D_ids[point2D_idxs] = tri_ids
else:
xys = np.zeros((0, 2), float)
point3D_ids = np.full(0, -1, int)
image_id = image_ids[name]
image = Image(
id=image_id,
qvec=qvec,
tvec=t,
camera_id=camera_ids[name],
name=name.replace("png", "jpg"), # some hack required for RobotCar
xys=xys,
point3D_ids=point3D_ids,
)
images[image_id] = image
return cameras, images, points3D
def main(nvm, database, output, skip_points=False):
assert nvm.exists(), nvm
assert database.exists(), database
image_ids, camera_ids = recover_database_images_and_ids(database)
logger.info("Reading the NVM model...")
model = read_nvm_model(
nvm, database, image_ids, camera_ids, skip_points=skip_points
)
logger.info("Writing the COLMAP model...")
output.mkdir(exist_ok=True, parents=True)
write_model(*model, path=str(output), ext=".bin")
logger.info("Done.")
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--nvm", required=True, type=Path)
parser.add_argument("--database", required=True, type=Path)
parser.add_argument("--output", required=True, type=Path)
parser.add_argument("--skip_points", action="store_true")
args = parser.parse_args()
main(**args.__dict__)
|