ai_meshbuild
/
single_tools
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
single tools scripts
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1 Commit
1 Branch
0 Tags
500 KiB
 
Tree: 195a3406e0
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '195a3406e0'
${ noResults }
single_tools/create_depth_fast.py

1208 lines
42 KiB
Raw Blame History

import os
os.environ["EGL_PLATFORM"] = "surfaceless"
import open3d as o3d
import numpy as np
import json
import argparse
from concurrent.futures import ThreadPoolExecutor
from typing import List, Tuple, Optional
# from scripts.colmap_loader import read_images_text, read_cameras_text
#
# Copyright (C) 2023, Inria
# GRAPHDECO research group, https://team.inria.fr/graphdeco
# All rights reserved.
#
# This software is free for non-commercial, research and evaluation use
# under the terms of the LICENSE.md file.
#
# For inquiries contact george.drettakis@inria.fr
#
import numpy as np
import collections
import struct
import math
import os
CameraModel = collections.namedtuple(
"CameraModel", ["model_id", "model_name", "num_params"]
)
Camera = collections.namedtuple("Camera", ["id", "model", "width", "height", "params"])
BaseImage = collections.namedtuple(
"Image", ["id", "qvec", "tvec", "camera_id", "name", "xys", "point3D_ids"]
)
Point3D = collections.namedtuple(
"Point3D", ["id", "xyz", "rgb", "error", "image_ids", "point2D_idxs"]
)
CAMERA_MODELS = {
CameraModel(model_id=0, model_name="SIMPLE_PINHOLE", num_params=3),
CameraModel(model_id=1, model_name="PINHOLE", num_params=4),
CameraModel(model_id=2, model_name="SIMPLE_RADIAL", num_params=4),
CameraModel(model_id=3, model_name="RADIAL", num_params=5),
CameraModel(model_id=4, model_name="OPENCV", num_params=8),
CameraModel(model_id=5, model_name="OPENCV_FISHEYE", num_params=8),
CameraModel(model_id=6, model_name="FULL_OPENCV", num_params=12),
CameraModel(model_id=7, model_name="FOV", num_params=5),
CameraModel(model_id=8, model_name="SIMPLE_RADIAL_FISHEYE", num_params=4),
CameraModel(model_id=9, model_name="RADIAL_FISHEYE", num_params=5),
CameraModel(model_id=10, model_name="THIN_PRISM_FISHEYE", num_params=12),
}
CAMERA_MODEL_IDS = dict(
[(camera_model.model_id, camera_model) for camera_model in CAMERA_MODELS]
)
CAMERA_MODEL_NAMES = dict(
[(camera_model.model_name, camera_model) for camera_model in CAMERA_MODELS]
)
def qvec2rotmat(qvec):
return np.array(
[
[
1 - 2 * qvec[2] ** 2 - 2 * qvec[3] ** 2,
2 * qvec[1] * qvec[2] - 2 * qvec[0] * qvec[3],
2 * qvec[3] * qvec[1] + 2 * qvec[0] * qvec[2],
],
[
2 * qvec[1] * qvec[2] + 2 * qvec[0] * qvec[3],
1 - 2 * qvec[1] ** 2 - 2 * qvec[3] ** 2,
2 * qvec[2] * qvec[3] - 2 * qvec[0] * qvec[1],
],
[
2 * qvec[3] * qvec[1] - 2 * qvec[0] * qvec[2],
2 * qvec[2] * qvec[3] + 2 * qvec[0] * qvec[1],
1 - 2 * qvec[1] ** 2 - 2 * qvec[2] ** 2,
],
]
)
def rotmat2qvec(R):
Rxx, Ryx, Rzx, Rxy, Ryy, Rzy, Rxz, Ryz, Rzz = R.flat
K = (
np.array(
[
[Rxx - Ryy - Rzz, 0, 0, 0],
[Ryx + Rxy, Ryy - Rxx - Rzz, 0, 0],
[Rzx + Rxz, Rzy + Ryz, Rzz - Rxx - Ryy, 0],
[Ryz - Rzy, Rzx - Rxz, Rxy - Ryx, Rxx + Ryy + Rzz],
]
)
/ 3.0
)
eigvals, eigvecs = np.linalg.eigh(K)
qvec = eigvecs[[3, 0, 1, 2], np.argmax(eigvals)]
if qvec[0] < 0:
qvec *= -1
return qvec
class Image(BaseImage):
def qvec2rotmat(self):
return qvec2rotmat(self.qvec)
def read_next_bytes(fid, num_bytes, format_char_sequence, endian_character="<"):
"""Read and unpack the next bytes from a binary file.
:param fid:
:param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc.
:param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}.
:param endian_character: Any of {@, =, <, >, !}
:return: Tuple of read and unpacked values.
"""
data = fid.read(num_bytes)
return struct.unpack(endian_character + format_char_sequence, data)
def read_points3D_text(path):
"""
see: src/base/reconstruction.cc
void Reconstruction::ReadPoints3DText(const std::string& path)
void Reconstruction::WritePoints3DText(const std::string& path)
"""
xyzs = None
rgbs = None
errors = None
num_points = 0
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
num_points += 1
xyzs = np.empty((num_points, 3))
rgbs = np.empty((num_points, 3))
errors = np.empty((num_points, 1))
count = 0
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
xyz = np.array(tuple(map(float, elems[1:4])))
rgb = np.array(tuple(map(int, elems[4:7])))
error = np.array(float(elems[7]))
xyzs[count] = xyz
rgbs[count] = rgb
errors[count] = error
count += 1
return xyzs, rgbs, errors
def read_points3D_binary(path_to_model_file):
"""
see: src/base/reconstruction.cc
void Reconstruction::ReadPoints3DBinary(const std::string& path)
void Reconstruction::WritePoints3DBinary(const std::string& path)
"""
with open(path_to_model_file, "rb") as fid:
num_points = read_next_bytes(fid, 8, "Q")[0]
xyzs = np.empty((num_points, 3))
rgbs = np.empty((num_points, 3))
errors = np.empty((num_points, 1))
for p_id in range(num_points):
binary_point_line_properties = read_next_bytes(
fid, num_bytes=43, format_char_sequence="QdddBBBd"
)
xyz = np.array(binary_point_line_properties[1:4])
rgb = np.array(binary_point_line_properties[4:7])
error = np.array(binary_point_line_properties[7])
track_length = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[
0
]
track_elems = read_next_bytes(
fid,
num_bytes=8 * track_length,
format_char_sequence="ii" * track_length,
)
xyzs[p_id] = xyz
rgbs[p_id] = rgb
errors[p_id] = error
return xyzs, rgbs, errors
def read_intrinsics_text(path):
"""
Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_write_model.py
"""
cameras = {}
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
camera_id = int(elems[0])
model = elems[1]
assert (
model == "PINHOLE"
), "While the loader support other types, the rest of the code assumes PINHOLE"
width = int(elems[2])
height = int(elems[3])
params = np.array(tuple(map(float, elems[4:])))
cameras[camera_id] = Camera(
id=camera_id, model=model, width=width, height=height, params=params
)
return cameras
def read_extrinsics_binary(path_to_model_file):
"""
see: src/base/reconstruction.cc
void Reconstruction::ReadImagesBinary(const std::string& path)
void Reconstruction::WriteImagesBinary(const std::string& path)
"""
images = {}
with open(path_to_model_file, "rb") as fid:
num_reg_images = read_next_bytes(fid, 8, "Q")[0]
for _ in range(num_reg_images):
binary_image_properties = read_next_bytes(
fid, num_bytes=64, format_char_sequence="idddddddi"
)
image_id = binary_image_properties[0]
qvec = np.array(binary_image_properties[1:5])
tvec = np.array(binary_image_properties[5:8])
camera_id = binary_image_properties[8]
image_name = ""
current_char = read_next_bytes(fid, 1, "c")[0]
while current_char != b"\x00": # look for the ASCII 0 entry
image_name += current_char.decode("utf-8")
current_char = read_next_bytes(fid, 1, "c")[0]
num_points2D = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[
0
]
x_y_id_s = read_next_bytes(
fid,
num_bytes=24 * num_points2D,
format_char_sequence="ddq" * num_points2D,
)
xys = np.column_stack(
[tuple(map(float, x_y_id_s[0::3])), tuple(map(float, x_y_id_s[1::3]))]
)
point3D_ids = np.array(tuple(map(int, x_y_id_s[2::3])))
images[image_id] = Image(
id=image_id,
qvec=qvec,
tvec=tvec,
camera_id=camera_id,
name=image_name,
xys=xys,
point3D_ids=point3D_ids,
)
return images
def read_intrinsics_binary(path_to_model_file):
"""
see: src/base/reconstruction.cc
void Reconstruction::WriteCamerasBinary(const std::string& path)
void Reconstruction::ReadCamerasBinary(const std::string& path)
"""
cameras = {}
with open(path_to_model_file, "rb") as fid:
num_cameras = read_next_bytes(fid, 8, "Q")[0]
for _ in range(num_cameras):
camera_properties = read_next_bytes(
fid, num_bytes=24, format_char_sequence="iiQQ"
)
camera_id = camera_properties[0]
model_id = camera_properties[1]
model_name = CAMERA_MODEL_IDS[camera_properties[1]].model_name
width = camera_properties[2]
height = camera_properties[3]
num_params = CAMERA_MODEL_IDS[model_id].num_params
params = read_next_bytes(
fid, num_bytes=8 * num_params, format_char_sequence="d" * num_params
)
cameras[camera_id] = Camera(
id=camera_id,
model=model_name,
width=width,
height=height,
params=np.array(params),
)
assert len(cameras) == num_cameras
return cameras
def focal2fov(focal, pixels):
return 2 * math.atan(pixels / (2 * focal))
def read_extrinsics_text(path):
"""
Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_write_model.py
"""
images = {}
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
image_id = int(elems[0])
qvec = np.array(tuple(map(float, elems[1:5])))
tvec = np.array(tuple(map(float, elems[5:8])))
camera_id = int(elems[8])
image_name = elems[9]
elems = fid.readline().split()
xys = np.column_stack(
[tuple(map(float, elems[0::3])), tuple(map(float, elems[1::3]))]
)
point3D_ids = np.array(tuple(map(int, elems[2::3])))
images[image_id] = Image(
id=image_id,
qvec=qvec,
tvec=tvec,
camera_id=camera_id,
name=image_name,
xys=xys,
point3D_ids=point3D_ids,
)
return images
def read_colmap_bin_array(path):
"""
Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_dense.py
:param path: path to the colmap binary file.
:return: nd array with the floating point values in the value
"""
with open(path, "rb") as fid:
width, height, channels = np.genfromtxt(
fid, delimiter="&", max_rows=1, usecols=(0, 1, 2), dtype=int
)
fid.seek(0)
num_delimiter = 0
byte = fid.read(1)
while True:
if byte == b"&":
num_delimiter += 1
if num_delimiter >= 3:
break
byte = fid.read(1)
array = np.fromfile(fid, np.float32)
array = array.reshape((width, height, channels), order="F")
return np.transpose(array, (1, 0, 2)).squeeze()
def read_next_bytes(fid, num_bytes, format_char_sequence, endian_character="<"):
"""Read and unpack the next bytes from a binary file.
:param fid:
:param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc.
:param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}.
:param endian_character: Any of {@, =, <, >, !}
:return: Tuple of read and unpacked values.
"""
data = fid.read(num_bytes)
return struct.unpack(endian_character + format_char_sequence, data)
def write_next_bytes(fid, data, format_char_sequence, endian_character="<"):
"""pack and write to a binary file.
:param fid:
:param data: data to send, if multiple elements are sent at the same time,
they should be encapsuled either in a list or a tuple
:param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}.
should be the same length as the data list or tuple
:param endian_character: Any of {@, =, <, >, !}
"""
if isinstance(data, (list, tuple)):
bytes = struct.pack(endian_character + format_char_sequence, *data)
else:
bytes = struct.pack(endian_character + format_char_sequence, data)
fid.write(bytes)
def read_cameras_text(path):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::WriteCamerasText(const std::string& path)
void Reconstruction::ReadCamerasText(const std::string& path)
"""
cameras = {}
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
camera_id = int(elems[0])
model = elems[1]
width = int(elems[2])
height = int(elems[3])
params = np.array(tuple(map(float, elems[4:])))
cameras[camera_id] = Camera(
id=camera_id,
model=model,
width=width,
height=height,
params=params,
)
return cameras
def read_cameras_binary(path_to_model_file):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::WriteCamerasBinary(const std::string& path)
void Reconstruction::ReadCamerasBinary(const std::string& path)
"""
cameras = {}
with open(path_to_model_file, "rb") as fid:
num_cameras = read_next_bytes(fid, 8, "Q")[0]
for _ in range(num_cameras):
camera_properties = read_next_bytes(
fid, num_bytes=24, format_char_sequence="iiQQ"
)
camera_id = camera_properties[0]
model_id = camera_properties[1]
model_name = CAMERA_MODEL_IDS[camera_properties[1]].model_name
width = camera_properties[2]
height = camera_properties[3]
num_params = CAMERA_MODEL_IDS[model_id].num_params
params = read_next_bytes(
fid,
num_bytes=8 * num_params,
format_char_sequence="d" * num_params,
)
cameras[camera_id] = Camera(
id=camera_id,
model=model_name,
width=width,
height=height,
params=np.array(params),
)
assert len(cameras) == num_cameras
return cameras
def write_cameras_text(cameras, path):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::WriteCamerasText(const std::string& path)
void Reconstruction::ReadCamerasText(const std::string& path)
"""
HEADER = (
"# Camera list with one line of data per camera:\n"
+ "# CAMERA_ID, MODEL, WIDTH, HEIGHT, PARAMS[]\n"
+ "# Number of cameras: {}\n".format(len(cameras))
)
with open(path, "w") as fid:
fid.write(HEADER)
for _, cam in cameras.items():
to_write = [cam.id, cam.model, cam.width, cam.height, *cam.params]
line = " ".join([str(elem) for elem in to_write])
fid.write(line + "\n")
def write_cameras_binary(cameras, path_to_model_file):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::WriteCamerasBinary(const std::string& path)
void Reconstruction::ReadCamerasBinary(const std::string& path)
"""
with open(path_to_model_file, "wb") as fid:
write_next_bytes(fid, len(cameras), "Q")
for _, cam in cameras.items():
model_id = CAMERA_MODEL_NAMES[cam.model].model_id
camera_properties = [cam.id, model_id, cam.width, cam.height]
write_next_bytes(fid, camera_properties, "iiQQ")
for p in cam.params:
write_next_bytes(fid, float(p), "d")
return cameras
def read_images_text(path):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadImagesText(const std::string& path)
void Reconstruction::WriteImagesText(const std::string& path)
"""
images = {}
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
image_id = int(elems[0])
qvec = np.array(tuple(map(float, elems[1:5])))
tvec = np.array(tuple(map(float, elems[5:8])))
camera_id = int(elems[8])
image_name = elems[9]
elems = fid.readline().split()
xys = np.column_stack(
[
tuple(map(float, elems[0::3])),
tuple(map(float, elems[1::3])),
]
)
point3D_ids = np.array(tuple(map(int, elems[2::3])))
images[image_id] = Image(
id=image_id,
qvec=qvec,
tvec=tvec,
camera_id=camera_id,
name=image_name,
xys=xys,
point3D_ids=point3D_ids,
)
return images
def read_images_binary(path_to_model_file):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadImagesBinary(const std::string& path)
void Reconstruction::WriteImagesBinary(const std::string& path)
"""
images = {}
with open(path_to_model_file, "rb") as fid:
num_reg_images = read_next_bytes(fid, 8, "Q")[0]
for _ in range(num_reg_images):
binary_image_properties = read_next_bytes(
fid, num_bytes=64, format_char_sequence="idddddddi"
)
image_id = binary_image_properties[0]
qvec = np.array(binary_image_properties[1:5])
tvec = np.array(binary_image_properties[5:8])
camera_id = binary_image_properties[8]
binary_image_name = b""
current_char = read_next_bytes(fid, 1, "c")[0]
while current_char != b"\x00": # look for the ASCII 0 entry
binary_image_name += current_char
current_char = read_next_bytes(fid, 1, "c")[0]
image_name = binary_image_name.decode("utf-8")
num_points2D = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[
0
]
x_y_id_s = read_next_bytes(
fid,
num_bytes=24 * num_points2D,
format_char_sequence="ddq" * num_points2D,
)
xys = np.column_stack(
[
tuple(map(float, x_y_id_s[0::3])),
tuple(map(float, x_y_id_s[1::3])),
]
)
point3D_ids = np.array(tuple(map(int, x_y_id_s[2::3])))
images[image_id] = Image(
id=image_id,
qvec=qvec,
tvec=tvec,
camera_id=camera_id,
name=image_name,
xys=xys,
point3D_ids=point3D_ids,
)
return images
def write_images_text(images, path):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadImagesText(const std::string& path)
void Reconstruction::WriteImagesText(const std::string& path)
"""
if len(images) == 0:
mean_observations = 0
else:
mean_observations = sum(
(len(img.point3D_ids) for _, img in images.items())
) / len(images)
HEADER = (
"# Image list with two lines of data per image:\n"
+ "# IMAGE_ID, QW, QX, QY, QZ, TX, TY, TZ, CAMERA_ID, NAME\n"
+ "# POINTS2D[] as (X, Y, POINT3D_ID)\n"
+ "# Number of images: {}, mean observations per image: {}\n".format(
len(images), mean_observations
)
)
with open(path, "w") as fid:
fid.write(HEADER)
for _, img in images.items():
image_header = [
img.id,
*img.qvec,
*img.tvec,
img.camera_id,
img.name,
]
first_line = " ".join(map(str, image_header))
fid.write(first_line + "\n")
points_strings = []
for xy, point3D_id in zip(img.xys, img.point3D_ids):
points_strings.append(" ".join(map(str, [*xy, point3D_id])))
fid.write(" ".join(points_strings) + "\n")
def write_images_binary(images, path_to_model_file):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadImagesBinary(const std::string& path)
void Reconstruction::WriteImagesBinary(const std::string& path)
"""
with open(path_to_model_file, "wb") as fid:
write_next_bytes(fid, len(images), "Q")
for _, img in images.items():
write_next_bytes(fid, img.id, "i")
write_next_bytes(fid, img.qvec.tolist(), "dddd")
write_next_bytes(fid, img.tvec.tolist(), "ddd")
write_next_bytes(fid, img.camera_id, "i")
for char in img.name:
write_next_bytes(fid, char.encode("utf-8"), "c")
write_next_bytes(fid, b"\x00", "c")
write_next_bytes(fid, len(img.point3D_ids), "Q")
for xy, p3d_id in zip(img.xys, img.point3D_ids):
write_next_bytes(fid, [*xy, p3d_id], "ddq")
def read_points3D_text(path):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadPoints3DText(const std::string& path)
void Reconstruction::WritePoints3DText(const std::string& path)
"""
points3D = {}
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
point3D_id = int(elems[0])
xyz = np.array(tuple(map(float, elems[1:4])))
rgb = np.array(tuple(map(int, elems[4:7])))
error = float(elems[7])
image_ids = np.array(tuple(map(int, elems[8::2])))
point2D_idxs = np.array(tuple(map(int, elems[9::2])))
points3D[point3D_id] = Point3D(
id=point3D_id,
xyz=xyz,
rgb=rgb,
error=error,
image_ids=image_ids,
point2D_idxs=point2D_idxs,
)
return points3D
def read_points3D_binary(path_to_model_file):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadPoints3DBinary(const std::string& path)
void Reconstruction::WritePoints3DBinary(const std::string& path)
"""
points3D = {}
with open(path_to_model_file, "rb") as fid:
num_points = read_next_bytes(fid, 8, "Q")[0]
for _ in range(num_points):
binary_point_line_properties = read_next_bytes(
fid, num_bytes=43, format_char_sequence="QdddBBBd"
)
point3D_id = binary_point_line_properties[0]
xyz = np.array(binary_point_line_properties[1:4])
rgb = np.array(binary_point_line_properties[4:7])
error = np.array(binary_point_line_properties[7])
track_length = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[
0
]
track_elems = read_next_bytes(
fid,
num_bytes=8 * track_length,
format_char_sequence="ii" * track_length,
)
image_ids = np.array(tuple(map(int, track_elems[0::2])))
point2D_idxs = np.array(tuple(map(int, track_elems[1::2])))
points3D[point3D_id] = Point3D(
id=point3D_id,
xyz=xyz,
rgb=rgb,
error=error,
image_ids=image_ids,
point2D_idxs=point2D_idxs,
)
return points3D
def write_points3D_text(points3D, path):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadPoints3DText(const std::string& path)
void Reconstruction::WritePoints3DText(const std::string& path)
"""
if len(points3D) == 0:
mean_track_length = 0
else:
mean_track_length = sum(
(len(pt.image_ids) for _, pt in points3D.items())
) / len(points3D)
HEADER = (
"# 3D point list with one line of data per point:\n"
+ "# POINT3D_ID, X, Y, Z, R, G, B, ERROR, TRACK[] as (IMAGE_ID, POINT2D_IDX)\n"
+ "# Number of points: {}, mean track length: {}\n".format(
len(points3D), mean_track_length
)
)
with open(path, "w") as fid:
fid.write(HEADER)
for _, pt in points3D.items():
point_header = [pt.id, *pt.xyz, *pt.rgb, pt.error]
fid.write(" ".join(map(str, point_header)) + " ")
track_strings = []
for image_id, point2D in zip(pt.image_ids, pt.point2D_idxs):
track_strings.append(" ".join(map(str, [image_id, point2D])))
fid.write(" ".join(track_strings) + "\n")
def write_points3D_binary(points3D, path_to_model_file):
"""
see: src/colmap/scene/reconstruction.cc
void Reconstruction::ReadPoints3DBinary(const std::string& path)
void Reconstruction::WritePoints3DBinary(const std::string& path)
"""
with open(path_to_model_file, "wb") as fid:
write_next_bytes(fid, len(points3D), "Q")
for _, pt in points3D.items():
write_next_bytes(fid, pt.id, "Q")
write_next_bytes(fid, pt.xyz.tolist(), "ddd")
write_next_bytes(fid, pt.rgb.tolist(), "BBB")
write_next_bytes(fid, pt.error, "d")
track_length = pt.image_ids.shape[0]
write_next_bytes(fid, track_length, "Q")
for image_id, point2D_id in zip(pt.image_ids, pt.point2D_idxs):
write_next_bytes(fid, [image_id, point2D_id], "ii")
def detect_model_format(path, ext):
if (
os.path.isfile(os.path.join(path, "cameras" + ext))
and os.path.isfile(os.path.join(path, "images" + ext))
and os.path.isfile(os.path.join(path, "points3D" + ext))
):
print("Detected model format: '" + ext + "'")
return True
return False
def read_model(path, ext=""):
# try to detect the extension automatically
if ext == "":
if detect_model_format(path, ".bin"):
ext = ".bin"
elif detect_model_format(path, ".txt"):
ext = ".txt"
else:
print("Provide model format: '.bin' or '.txt'")
return
if ext == ".txt":
cameras = read_cameras_text(os.path.join(path, "cameras" + ext))
images = read_images_text(os.path.join(path, "images" + ext))
points3D = read_points3D_text(os.path.join(path, "points3D") + ext)
else:
cameras = read_cameras_binary(os.path.join(path, "cameras" + ext))
images = read_images_binary(os.path.join(path, "images" + ext))
points3D = read_points3D_binary(os.path.join(path, "points3D") + ext)
return cameras, images, points3D
def write_model(cameras, images, points3D, path, ext=".bin"):
if ext == ".txt":
write_cameras_text(cameras, os.path.join(path, "cameras" + ext))
write_images_text(images, os.path.join(path, "images" + ext))
write_points3D_text(points3D, os.path.join(path, "points3D") + ext)
else:
write_cameras_binary(cameras, os.path.join(path, "cameras" + ext))
write_images_binary(images, os.path.join(path, "images" + ext))
write_points3D_binary(points3D, os.path.join(path, "points3D") + ext)
return cameras, images, points3D
def qvec2rotmat(qvec):
return np.array(
[
[
1 - 2 * qvec[2] ** 2 - 2 * qvec[3] ** 2,
2 * qvec[1] * qvec[2] - 2 * qvec[0] * qvec[3],
2 * qvec[3] * qvec[1] + 2 * qvec[0] * qvec[2],
],
[
2 * qvec[1] * qvec[2] + 2 * qvec[0] * qvec[3],
1 - 2 * qvec[1] ** 2 - 2 * qvec[3] ** 2,
2 * qvec[2] * qvec[3] - 2 * qvec[0] * qvec[1],
],
[
2 * qvec[3] * qvec[1] - 2 * qvec[0] * qvec[2],
2 * qvec[2] * qvec[3] + 2 * qvec[0] * qvec[1],
1 - 2 * qvec[1] ** 2 - 2 * qvec[2] ** 2,
],
]
)
def rotmat2qvec(R):
Rxx, Ryx, Rzx, Rxy, Ryy, Rzy, Rxz, Ryz, Rzz = R.flat
K = (
np.array(
[
[Rxx - Ryy - Rzz, 0, 0, 0],
[Ryx + Rxy, Ryy - Rxx - Rzz, 0, 0],
[Rzx + Rxz, Rzy + Ryz, Rzz - Rxx - Ryy, 0],
[Ryz - Rzy, Rzx - Rxz, Rxy - Ryx, Rxx + Ryy + Rzz],
]
)
/ 3.0
)
eigvals, eigvecs = np.linalg.eigh(K)
qvec = eigvecs[[3, 0, 1, 2], np.argmax(eigvals)]
if qvec[0] < 0:
qvec *= -1
return qvec
class DepthRenderer:
"""
复用渲染器的深度图渲染类
"""
def __init__(self, mesh: o3d.geometry.TriangleMesh, width: int, height: int):
"""
初始化渲染器，只加载一次模型
参数:
mesh (o3d.geometry.TriangleMesh): 要渲染的3D网格
width (int): 渲染图像的宽度
height (int): 渲染图像的高度
"""
self.width = width
self.height = height
# 创建渲染器（只创建一次）
self.render = o3d.visualization.rendering.OffscreenRenderer(width, height)
# 将 mesh 加载到渲染器（只加载一次）
material = o3d.visualization.rendering.MaterialRecord()
self.render.scene.add_geometry("mesh", mesh, material)
# 确保渲染器正确初始化
if not self.render:
raise RuntimeError("Renderer failed to initialize.")
def render_depth_map(self, K: np.ndarray, R: np.ndarray, t: np.ndarray) -> Tuple[np.ndarray, float]:
"""
渲染深度图，复用已初始化的渲染器
参数:
K (np.array): 相机内参矩阵
R (np.array): 相机旋转矩阵
t (np.array): 相机平移向量
返回:
tuple: 包含深度图（未归一化）和最大深度值
"""
# 设置相机投影矩阵
fx, fy, cx, cy = K[0, 0], K[1, 1], K[0, 2], K[1, 2]
intrinsic = o3d.camera.PinholeCameraIntrinsic(self.width, self.height, fx, fy, cx, cy)
# 将外参转换为 4x4 变换矩阵 (从 R 和 t)
extrinsic = np.eye(4)
extrinsic[:3, :3] = R
extrinsic[:3, 3] = t
# 设置相机参数（只需要更新相机参数）
self.render.setup_camera(intrinsic, extrinsic)
# 渲染深度图
depth_image = self.render.render_to_depth_image(z_in_view_space=True)
# 检查是否生成了深度图
if depth_image is None:
raise RuntimeError("Depth image was not generated.")
# 将深度图转换为 numpy 数组
depth_map = np.asarray(depth_image)
# 返回未归一化的深度图和最大深度值
max_depth = np.nanmax(depth_map) # 获取最大深度值
return depth_map, max_depth
def save_depth_map_async(depth_data: Tuple[str, np.ndarray, float], output_path: str) -> None:
"""
异步保存深度图的函数
参数:
depth_data: 包含(文件名, 深度图, 最大深度值)的元组
output_path: 输出路径
"""
name, depth_map, max_depth = depth_data
depth_filename = os.path.join(output_path, f"{name.split('.')[0]}.npz")
np.savez_compressed(depth_filename, depth=depth_map, max_depth=max_depth)
def generate_depth_maps_and_save_optimized(
mesh: o3d.geometry.TriangleMesh,
camera_params: List[Tuple[str, np.ndarray, np.ndarray, np.ndarray]],
width: int,
height: int,
output_path: str,
max_workers: Optional[int] = None
) -> None:
"""
优化版本：生成深度图并异步保存
参数:
mesh (o3d.geometry.TriangleMesh): 3D网格
camera_params (list): 相机参数列表
width (int): 图像宽度
height (int): 图像高度
output_path (str): 输出路径
max_workers (int, optional): 异步保存的最大工作线程数
返回:
None
"""
# 确保输出目录存在
os.makedirs(output_path, exist_ok=True)
# 创建复用的深度渲染器
depth_renderer = DepthRenderer(mesh, width, height)
# 存储待保存的深度图数据
depth_data_list = []
print(f"开始渲染 {len(camera_params)} 张深度图...")
# 批量渲染深度图
for i, (name, K, R, t) in enumerate(camera_params):
depth_map, max_depth = depth_renderer.render_depth_map(K, R, t)
depth_data_list.append((name, depth_map.copy(), max_depth))
if (i + 1) % 10 == 0:
print(f"已渲染 {i + 1}/{len(camera_params)} 张图片")
print("渲染完成，开始异步保存...")
# 使用线程池异步保存所有深度图
with ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = []
for depth_data in depth_data_list:
future = executor.submit(save_depth_map_async, depth_data, output_path)
futures.append(future)
# 等待所有保存任务完成，并显示进度
for i, future in enumerate(futures):
future.result() # 等待完成并获取结果（如果有异常会抛出）
if (i + 1) % 10 == 0:
print(f"已保存 {i + 1}/{len(futures)} 个文件")
print(f"所有深度图已保存完成到: {output_path}")
def render_depth_map(mesh, K, R, t, width, height):
"""
渲染深度图，不进行归一化。
注意：此函数保留用于向后兼容，建议使用 DepthRenderer 类以获得更好的性能
参数:
mesh (o3d.geometry.TriangleMesh): 要渲染的3D网格
K (np.array): 相机内参矩阵
R (np.array): 相机旋转矩阵
t (np.array): 相机平移向量
width (int): 渲染图像的宽度
height (int): 渲染图像的高度
返回:
tuple: 包含深度图（未归一化）和最大深度值
"""
# 创建渲染器
render = o3d.visualization.rendering.OffscreenRenderer(width, height)
# 设置相机投影矩阵
fx, fy, cx, cy = K[0, 0], K[1, 1], K[0, 2], K[1, 2]
intrinsic = o3d.camera.PinholeCameraIntrinsic(width, height, fx, fy, cx, cy)
# 将外参转换为 4x4 变换矩阵 (从 R 和 t)
extrinsic = np.eye(4)
extrinsic[:3, :3] = R
extrinsic[:3, 3] = t
# 设置相机参数
render.setup_camera(intrinsic, extrinsic)
# 将 mesh 加载到渲染器
material = o3d.visualization.rendering.MaterialRecord()
render.scene.add_geometry("mesh", mesh, material)
# 渲染深度图
depth_image = render.render_to_depth_image(z_in_view_space=True)
# 确保渲染器正确初始化
if not render:
raise RuntimeError("Renderer failed to initialize.")
# 检查是否生成了深度图
if depth_image is None:
raise RuntimeError("Depth image was not generated.")
# 将深度图转换为 numpy 数组
depth_map = np.asarray(depth_image)
# 返回未归一化的深度图和最大深度值
max_depth = np.nanmax(depth_map) # 获取最大深度值
return depth_map, max_depth
def load_camera_parameters(colmap_params_path):
"""
从COLMAP参数文件加载相机参数。
参数:
colmap_params_path (str): COLMAP参数文件的路径
返回:
tuple: 包含相机参数列表、图像宽度和高度
"""
images = read_images_text(f"{colmap_params_path}/images.txt")
cameras = read_cameras_text(f"{colmap_params_path}/cameras.txt")
camera_params = []
for image_id, image in images.items():
camera_id = image.camera_id
camera = cameras[camera_id]
# 读取内参 相机内参可以获取 fx, fy, cx, cy
K = np.array(
[
[camera.params[0], 0, camera.params[2]],
[0, camera.params[1], camera.params[3]],
[0, 0, 1],
]
)
# 读取外参 相机外参可以获取 qvec 和 tvec
R = image.qvec2rotmat()
t = np.array(image.tvec)
camera_params.append((image.name, K, R, t))
return camera_params, camera.width, camera.height
def generate_depth_maps_and_save(mesh, camera_params, width, height, output_path):
"""
生成深度图并保存为 .npy 格式。
注意：此函数保留用于向后兼容，建议使用 generate_depth_maps_and_save_optimized 以获得更好的性能
参数:
mesh (o3d.geometry.TriangleMesh): 3D网格
camera_params (list): 相机参数列表
width (int): 图像宽度
height (int): 图像高度
output_path (str): 输出路径
返回:
None
"""
# 调用优化版本
generate_depth_maps_and_save_optimized(mesh, camera_params, width, height, output_path)
def create_depth_maps(mesh_path, colmap_params_path, output_path, use_optimized=True, max_workers=None):
"""
创建深度图并保存为 .npz 格式。
参数:
mesh_path (str): 3D网格文件路径
colmap_params_path (str): COLMAP参数文件路径
output_path (str): 输出路径
use_optimized (bool): 是否使用优化版本（默认True）
max_workers (int, optional): 异步保存的最大工作线程数
返回:
None
"""
print(f"加载3D网格: {mesh_path}")
# 加载 3D 网格
mesh = o3d.io.read_triangle_mesh(mesh_path)
if len(mesh.vertices) == 0:
raise ValueError(f"无法加载网格文件或网格为空: {mesh_path}")
print(f"加载相机参数: {colmap_params_path}")
# 加载相机参数
camera_params, width, height = load_camera_parameters(colmap_params_path)
print(f"找到 {len(camera_params)} 个相机参数")
print(f"图像尺寸: {width} x {height}")
# 使用优化版本生成并保存深度图
if use_optimized:
generate_depth_maps_and_save_optimized(mesh, camera_params, width, height, output_path, max_workers)
else:
# 使用原始版本
for i, (name, K, R, t) in enumerate(camera_params):
depth_map, max_depth = render_depth_map(mesh, K, R, t, width, height)
# 保存深度图为 .npz 文件
depth_filename = f"{output_path}/{name.split('.')[0]}.npz"
np.savez_compressed(depth_filename, depth=depth_map, max_depth=max_depth)
if (i + 1) % 10 == 0:
print(f"已处理 {i + 1}/{len(camera_params)} 张图片")
# 示例用法
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Generate depth maps from a mesh and colmap parameters"
)
parser.add_argument("--mesh_path", type=str, required=True, help="Path to the mesh file")
parser.add_argument(
"--colmap_params_path", type=str, required=True, help="Path to the colmap parameters"
)
parser.add_argument("--output_path", type=str, required=True, help="Path to the output directory")
parser.add_argument(
"--use_optimized",
action="store_true",
default=True,
help="Use optimized version with renderer reuse and async I/O (default: True)"
)
parser.add_argument(
"--no_optimized",
action="store_true",
help="Use original version (slower)"
)
parser.add_argument(
"--max_workers",
type=int,
default=None,
help="Maximum number of worker threads for async I/O (default: None, uses system default)"
)
args = parser.parse_args()
# 如果指定了 --no_optimized，则使用原始版本
use_optimized = not args.no_optimized
import time
start_time = time.time()
print("=" * 50)
print("深度图生成工具")
print("=" * 50)
print(f"网格文件: {args.mesh_path}")
print(f"COLMAP参数路径: {args.colmap_params_path}")
print(f"输出路径: {args.output_path}")
print(f"使用优化版本: {use_optimized}")
if use_optimized and args.max_workers:
print(f"最大工作线程数: {args.max_workers}")
print("=" * 50)
try:
create_depth_maps(
args.mesh_path,
args.colmap_params_path,
args.output_path,
use_optimized=use_optimized,
max_workers=args.max_workers
)
print(" 深度图生成完成！")
except Exception as e:
print(f" 生成深度图时出错: {e}")
raise e
elapsed_time = time.time() - start_time
minutes = int(elapsed_time // 60)
seconds = int(elapsed_time % 60)
print(f" 深度图生成完成，用时: {minutes}分{seconds}秒")