tink/nerfstudio
4
0 Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-12 19:04:03 +08:00
Code Activity

Add colmap preprocessing script (#338)

Browse Source 
* Add colmap preprocessing script

* Fix lint, add dataparser
This commit is contained in:
Matthew Tancik authored and GitHub committed 2022-09-04 17:39:30 -07:00
1 parent 18f8a5d0b8
commit 2ca0695fef
4 files changed
+399 -210
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

nerfactory/utils/colmap_utils.py
+331
View File
@@ -0,0 +1,331 @@
# pylint: disable-all
"""
Here we have modified code taken from COLMAP for parsing data in the COLMAP format.
Original file at https://github.com/colmap/colmap/blob/1a4d0bad2e90aa65ce997c9d1779518eaed998d5/scripts/python/read_write_model.py.
"""
# Copyright (c) 2022, ETH Zurich and UNC Chapel Hill.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# * Neither the name of ETH Zurich and UNC Chapel Hill nor the names of
# its contributors may be used to endorse or promote products derived
# from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
# Author: Johannes L. Schoenberger (jsch-at-demuc-dot-de)
import argparse
import collections
import os
import struct
import numpy as np
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"])
class Image(BaseImage):
def qvec2rotmat(self):
return qvec2rotmat(self.qvec)
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 = {camera_model.model_id: camera_model for camera_model in CAMERA_MODELS}
CAMERA_MODEL_NAMES = {camera_model.model_name: camera_model for camera_model in CAMERA_MODELS}
def read_next_bytes(fid, num_bytes, format_char_sequence, endian_character="<"):
"""Read and unpack the next bytes from a binary file.
Args:
fid:
num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc.
format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}.
endian_character: Any of {@, =, <, >, !}
Tuple of read and unpacked values.
"""
data = fid.read(num_bytes)
return struct.unpack(endian_character + format_char_sequence, data)
def read_cameras_text(path):
"""
see: src/base/reconstruction.cc
void Reconstruction::WriteCamerasText(const std::string& path)
void Reconstruction::ReadCamerasText(const std::string& path)
"""
cameras = {}
with open(path) 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/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 read_images_text(path):
"""
see: src/base/reconstruction.cc
void Reconstruction::ReadImagesText(const std::string& path)
void Reconstruction::WriteImagesText(const std::string& path)
"""
images = {}
with open(path) 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/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_pointsTD_text(path):
"""
see: src/base/reconstruction.cc
void Reconstruction::ReadPoints3DText(const std::string& path)
void Reconstruction::WritePoints3DText(const std::string& path)
"""
points3D = {}
with open(path) 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_pointsTD_binary(path_to_model_file):
"""
see: src/base/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 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:
raise ValueError("Provide model format: '.bin' or '.txt'")
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_pointsTD_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_pointsTD_binary(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[np.array([3, 0, 1, 2]), np.argmax(eigvals)]
if qvec[0] < 0:
qvec *= -1
return qvec