File size: 22,849 Bytes
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
9223079
 
 
 
 
 
e15a186
 
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
 
 
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
 
 
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
 
 
9223079
 
 
 
 
 
 
e15a186
 
 
 
 
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
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
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
# Copyright (c) 2018, 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 os
import collections
import numpy as np
import struct
import argparse
import logging

logger = logging.getLogger(__name__)


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 = 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 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/base/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/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 write_cameras_text(cameras, path):
    """
    see: src/base/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/base/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/base/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/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 write_images_text(images, path):
    """
    see: src/base/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/base/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/base/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/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 write_points3D_text(points3D, path):
    """
    see: src/base/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/base/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))
    ):
        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:
            try:
                cameras, images, points3D = read_model(
                    os.path.join(path, "model/")
                )
                logger.warning(
                    "This SfM file structure was deprecated in hloc v1.1"
                )
                return cameras, images, points3D
            except FileNotFoundError:
                raise FileNotFoundError(
                    f"Could not find binary or text COLMAP model at {path}"
                )

    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


def main():
    parser = argparse.ArgumentParser(
        description="Read and write COLMAP binary and text models"
    )
    parser.add_argument("--input_model", help="path to input model folder")
    parser.add_argument(
        "--input_format",
        choices=[".bin", ".txt"],
        help="input model format",
        default="",
    )
    parser.add_argument("--output_model", help="path to output model folder")
    parser.add_argument(
        "--output_format",
        choices=[".bin", ".txt"],
        help="outut model format",
        default=".txt",
    )
    args = parser.parse_args()

    cameras, images, points3D = read_model(
        path=args.input_model, ext=args.input_format
    )

    print("num_cameras:", len(cameras))
    print("num_images:", len(images))
    print("num_points3D:", len(points3D))

    if args.output_model is not None:
        write_model(
            cameras,
            images,
            points3D,
            path=args.output_model,
            ext=args.output_format,
        )


if __name__ == "__main__":
    main()