Spaces:
Running
Running
File size: 16,618 Bytes
7088d16 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "bD6DUkgzmFoR"
},
"outputs": [],
"source": [
"# Copyright (c) Meta Platforms, Inc. and affiliates. All rights reserved."
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "Jj6j6__ZmFoW"
},
"source": [
"# Absolute camera orientation given set of relative camera pairs\n",
"\n",
"This tutorial showcases the `cameras`, `transforms` and `so3` API.\n",
"\n",
"The problem we deal with is defined as follows:\n",
"\n",
"Given an optical system of $N$ cameras with extrinsics $\\{g_1, ..., g_N | g_i \\in SE(3)\\}$, and a set of relative camera positions $\\{g_{ij} | g_{ij}\\in SE(3)\\}$ that map between coordinate frames of randomly selected pairs of cameras $(i, j)$, we search for the absolute extrinsic parameters $\\{g_1, ..., g_N\\}$ that are consistent with the relative camera motions.\n",
"\n",
"More formally:\n",
"$$\n",
"g_1, ..., g_N = \n",
"{\\arg \\min}_{g_1, ..., g_N} \\sum_{g_{ij}} d(g_{ij}, g_i^{-1} g_j),\n",
"$$,\n",
"where $d(g_i, g_j)$ is a suitable metric that compares the extrinsics of cameras $g_i$ and $g_j$. \n",
"\n",
"Visually, the problem can be described as follows. The picture below depicts the situation at the beginning of our optimization. The ground truth cameras are plotted in purple while the randomly initialized estimated cameras are plotted in orange:\n",
"\n",
"\n",
"Our optimization seeks to align the estimated (orange) cameras with the ground truth (purple) cameras, by minimizing the discrepancies between pairs of relative cameras. Thus, the solution to the problem should look as follows:\n",
"\n",
"\n",
"In practice, the camera extrinsics $g_{ij}$ and $g_i$ are represented using objects from the `SfMPerspectiveCameras` class initialized with the corresponding rotation and translation matrices `R_absolute` and `T_absolute` that define the extrinsic parameters $g = (R, T); R \\in SO(3); T \\in \\mathbb{R}^3$. In order to ensure that `R_absolute` is a valid rotation matrix, we represent it using an exponential map (implemented with `so3_exp_map`) of the axis-angle representation of the rotation `log_R_absolute`.\n",
"\n",
"Note that the solution to this problem could only be recovered up to an unknown global rigid transformation $g_{glob} \\in SE(3)$. Thus, for simplicity, we assume knowledge of the absolute extrinsics of the first camera $g_0$. We set $g_0$ as a trivial camera $g_0 = (I, \\vec{0})$.\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "nAQY4EnHmFoX"
},
"source": [
"## 0. Install and Import Modules"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "WAHR1LMJmP-h"
},
"source": [
"Ensure `torch` and `torchvision` are installed. If `pytorch3d` is not installed, install it using the following cell:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 717
},
"colab_type": "code",
"id": "uo7a3gdImMZx",
"outputId": "bf07fd03-dec0-4294-b2ba-9cf5b7333672"
},
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"import torch\n",
"import subprocess\n",
"need_pytorch3d=False\n",
"try:\n",
" import pytorch3d\n",
"except ModuleNotFoundError:\n",
" need_pytorch3d=True\n",
"if need_pytorch3d:\n",
" pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
" version_str=\"\".join([\n",
" f\"py3{sys.version_info.minor}_cu\",\n",
" torch.version.cuda.replace(\".\",\"\"),\n",
" f\"_pyt{pyt_version_str}\"\n",
" ])\n",
" !pip install fvcore iopath\n",
" if sys.platform.startswith(\"linux\"):\n",
" print(\"Trying to install wheel for PyTorch3D\")\n",
" !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
" pip_list = !pip freeze\n",
" need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for i in pip_list)\n",
" if need_pytorch3d:\n",
" print(f\"failed to find/install wheel for {version_str}\")\n",
"if need_pytorch3d:\n",
" print(\"Installing PyTorch3D from source\")\n",
" !pip install ninja\n",
" !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"colab_type": "code",
"id": "UgLa7XQimFoY",
"outputId": "16404f4f-4c7c-4f3f-b96a-e9a876def4c1"
},
"outputs": [],
"source": [
"# imports\n",
"import torch\n",
"from pytorch3d.transforms.so3 import (\n",
" so3_exp_map,\n",
" so3_relative_angle,\n",
")\n",
"from pytorch3d.renderer.cameras import (\n",
" SfMPerspectiveCameras,\n",
")\n",
"\n",
"# add path for demo utils\n",
"import sys\n",
"import os\n",
"sys.path.append(os.path.abspath(''))\n",
"\n",
"# set for reproducibility\n",
"torch.manual_seed(42)\n",
"if torch.cuda.is_available():\n",
" device = torch.device(\"cuda:0\")\n",
"else:\n",
" device = torch.device(\"cpu\")\n",
" print(\"WARNING: CPU only, this will be slow!\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "u4emnRuzmpRB"
},
"source": [
"If using **Google Colab**, fetch the utils file for plotting the camera scene, and the ground truth camera positions:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 391
},
"colab_type": "code",
"id": "kOvMPYJdmd15",
"outputId": "9f2a601b-891b-4cb6-d8f6-a444f7829132"
},
"outputs": [],
"source": [
"!wget https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/docs/tutorials/utils/camera_visualization.py\n",
"from camera_visualization import plot_camera_scene\n",
"\n",
"!mkdir data\n",
"!wget -P data https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/docs/tutorials/data/camera_graph.pth"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "L9WD5vaimw3K"
},
"source": [
"OR if running **locally** uncomment and run the following cell:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "ucGlQj5EmmJ5"
},
"outputs": [],
"source": [
"# from utils import plot_camera_scene"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "7WeEi7IgmFoc"
},
"source": [
"## 1. Set up Cameras and load ground truth positions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "D_Wm0zikmFod"
},
"outputs": [],
"source": [
"# load the SE3 graph of relative/absolute camera positions\n",
"camera_graph_file = './data/camera_graph.pth'\n",
"(R_absolute_gt, T_absolute_gt), \\\n",
" (R_relative, T_relative), \\\n",
" relative_edges = \\\n",
" torch.load(camera_graph_file)\n",
"\n",
"# create the relative cameras\n",
"cameras_relative = SfMPerspectiveCameras(\n",
" R = R_relative.to(device),\n",
" T = T_relative.to(device),\n",
" device = device,\n",
")\n",
"\n",
"# create the absolute ground truth cameras\n",
"cameras_absolute_gt = SfMPerspectiveCameras(\n",
" R = R_absolute_gt.to(device),\n",
" T = T_absolute_gt.to(device),\n",
" device = device,\n",
")\n",
"\n",
"# the number of absolute camera positions\n",
"N = R_absolute_gt.shape[0]"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "-f-RNlGemFog"
},
"source": [
"## 2. Define optimization functions\n",
"\n",
"### Relative cameras and camera distance\n",
"We now define two functions crucial for the optimization.\n",
"\n",
"**`calc_camera_distance`** compares a pair of cameras. This function is important as it defines the loss that we are minimizing. The method utilizes the `so3_relative_angle` function from the SO3 API.\n",
"\n",
"**`get_relative_camera`** computes the parameters of a relative camera that maps between a pair of absolute cameras. Here we utilize the `compose` and `inverse` class methods from the PyTorch3D Transforms API."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "xzzk88RHmFoh"
},
"outputs": [],
"source": [
"def calc_camera_distance(cam_1, cam_2):\n",
" \"\"\"\n",
" Calculates the divergence of a batch of pairs of cameras cam_1, cam_2.\n",
" The distance is composed of the cosine of the relative angle between \n",
" the rotation components of the camera extrinsics and the l2 distance\n",
" between the translation vectors.\n",
" \"\"\"\n",
" # rotation distance\n",
" R_distance = (1.-so3_relative_angle(cam_1.R, cam_2.R, cos_angle=True)).mean()\n",
" # translation distance\n",
" T_distance = ((cam_1.T - cam_2.T)**2).sum(1).mean()\n",
" # the final distance is the sum\n",
" return R_distance + T_distance\n",
"\n",
"def get_relative_camera(cams, edges):\n",
" \"\"\"\n",
" For each pair of indices (i,j) in \"edges\" generate a camera\n",
" that maps from the coordinates of the camera cams[i] to \n",
" the coordinates of the camera cams[j]\n",
" \"\"\"\n",
"\n",
" # first generate the world-to-view Transform3d objects of each \n",
" # camera pair (i, j) according to the edges argument\n",
" trans_i, trans_j = [\n",
" SfMPerspectiveCameras(\n",
" R = cams.R[edges[:, i]],\n",
" T = cams.T[edges[:, i]],\n",
" device = device,\n",
" ).get_world_to_view_transform()\n",
" for i in (0, 1)\n",
" ]\n",
" \n",
" # compose the relative transformation as g_i^{-1} g_j\n",
" trans_rel = trans_i.inverse().compose(trans_j)\n",
" \n",
" # generate a camera from the relative transform\n",
" matrix_rel = trans_rel.get_matrix()\n",
" cams_relative = SfMPerspectiveCameras(\n",
" R = matrix_rel[:, :3, :3],\n",
" T = matrix_rel[:, 3, :3],\n",
" device = device,\n",
" )\n",
" return cams_relative"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "Ys9J7MbMmFol"
},
"source": [
"## 3. Optimization\n",
"Finally, we start the optimization of the absolute cameras.\n",
"\n",
"We use SGD with momentum and optimize over `log_R_absolute` and `T_absolute`. \n",
"\n",
"As mentioned earlier, `log_R_absolute` is the axis angle representation of the rotation part of our absolute cameras. We can obtain the 3x3 rotation matrix `R_absolute` that corresponds to `log_R_absolute` with:\n",
"\n",
"`R_absolute = so3_exp_map(log_R_absolute)`\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"colab_type": "code",
"id": "iOK_DUzVmFom",
"outputId": "4195bc36-7b84-4070-dcc1-d3abb1e12031"
},
"outputs": [],
"source": [
"# initialize the absolute log-rotations/translations with random entries\n",
"log_R_absolute_init = torch.randn(N, 3, dtype=torch.float32, device=device)\n",
"T_absolute_init = torch.randn(N, 3, dtype=torch.float32, device=device)\n",
"\n",
"# furthermore, we know that the first camera is a trivial one \n",
"# (see the description above)\n",
"log_R_absolute_init[0, :] = 0.\n",
"T_absolute_init[0, :] = 0.\n",
"\n",
"# instantiate a copy of the initialization of log_R / T\n",
"log_R_absolute = log_R_absolute_init.clone().detach()\n",
"log_R_absolute.requires_grad = True\n",
"T_absolute = T_absolute_init.clone().detach()\n",
"T_absolute.requires_grad = True\n",
"\n",
"# the mask the specifies which cameras are going to be optimized\n",
"# (since we know the first camera is already correct, \n",
"# we only optimize over the 2nd-to-last cameras)\n",
"camera_mask = torch.ones(N, 1, dtype=torch.float32, device=device)\n",
"camera_mask[0] = 0.\n",
"\n",
"# init the optimizer\n",
"optimizer = torch.optim.SGD([log_R_absolute, T_absolute], lr=.1, momentum=0.9)\n",
"\n",
"# run the optimization\n",
"n_iter = 2000 # fix the number of iterations\n",
"for it in range(n_iter):\n",
" # re-init the optimizer gradients\n",
" optimizer.zero_grad()\n",
"\n",
" # compute the absolute camera rotations as \n",
" # an exponential map of the logarithms (=axis-angles)\n",
" # of the absolute rotations\n",
" R_absolute = so3_exp_map(log_R_absolute * camera_mask)\n",
"\n",
" # get the current absolute cameras\n",
" cameras_absolute = SfMPerspectiveCameras(\n",
" R = R_absolute,\n",
" T = T_absolute * camera_mask,\n",
" device = device,\n",
" )\n",
"\n",
" # compute the relative cameras as a composition of the absolute cameras\n",
" cameras_relative_composed = \\\n",
" get_relative_camera(cameras_absolute, relative_edges)\n",
"\n",
" # compare the composed cameras with the ground truth relative cameras\n",
" # camera_distance corresponds to $d$ from the description\n",
" camera_distance = \\\n",
" calc_camera_distance(cameras_relative_composed, cameras_relative)\n",
"\n",
" # our loss function is the camera_distance\n",
" camera_distance.backward()\n",
" \n",
" # apply the gradients\n",
" optimizer.step()\n",
"\n",
" # plot and print status message\n",
" if it % 200==0 or it==n_iter-1:\n",
" status = 'iteration=%3d; camera_distance=%1.3e' % (it, camera_distance)\n",
" plot_camera_scene(cameras_absolute, cameras_absolute_gt, status)\n",
"\n",
"print('Optimization finished.')\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "vncLMvxWnhmO"
},
"source": [
"## 4. Conclusion \n",
"\n",
"In this tutorial we learnt how to initialize a batch of SfM Cameras, set up loss functions for bundle adjustment, and run an optimization loop. "
]
}
],
"metadata": {
"accelerator": "GPU",
"bento_stylesheets": {
"bento/extensions/flow/main.css": true,
"bento/extensions/kernel_selector/main.css": true,
"bento/extensions/kernel_ui/main.css": true,
"bento/extensions/new_kernel/main.css": true,
"bento/extensions/system_usage/main.css": true,
"bento/extensions/theme/main.css": true
},
"colab": {
"name": "bundle_adjustment.ipynb",
"provenance": [],
"toc_visible": true
},
"file_extension": ".py",
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5+"
},
"mimetype": "text/x-python",
"name": "python",
"npconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": 3
},
"nbformat": 4,
"nbformat_minor": 1
}
|