nerfstudio/notebooks/visualize_viewer.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3c00934d-0f14-4c1a-a563-94d627b377e5",
   "metadata": {},
   "source": [
    "## Notebook to visualize the viewer functionality\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b15dfdc1-5054-40bc-9631-4c7426eecfd9",
   "metadata": {},
   "outputs": [],
   "source": [
    "from notebook_imports import *\n",
    "\n",
    "import time\n",
    "import torch\n",
    "from torch.utils.data import DataLoader\n",
    "\n",
    "from pyrad.data.dataloader import TrainDataloader\n",
    "from pyrad.data.image_dataset import ImageDataset, PanopticImageDataset\n",
    "from pyrad.data.image_sampler import CacheImageSampler\n",
    "from pyrad.data.pixel_sampler import PixelSampler\n",
    "from pyrad.data.utils import DatasetInputs, get_dataset_inputs_from_dataset_config\n",
    "from pyrad.graphs.modules.ray_generator import RayGenerator\n",
    "from pyrad.graphs.modules.scene_colliders import SceneBoundsCollider, AABBBoxCollider\n",
    "from pyrad.cameras.cameras import get_camera\n",
    "from pyrad.cameras.camera_paths import InterpolatedCameraPath\n",
    "from pyrad.cameras.rays import RayBundle\n",
    "from pyrad.utils.io import get_absolute_path\n",
    "from pyrad.utils.plotly import get_line_segments_from_lines\n",
    "from pyrad.cameras.cameras import get_camera_model\n",
    "from pyrad.utils.misc import get_dict_to_torch, instantiate_from_dict_config\n",
    "\n",
    "# the new import\n",
    "from pyrad.viewer.backend import vis_utils\n",
    "\n",
    "\n",
    "from hydra import compose, initialize\n",
    "from omegaconf import open_dict\n",
    "import pprint\n",
    "from tqdm import tqdm\n",
    "import random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "df82e083-e261-43e0-a1dc-05c6a59d16e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# establish the connection to the tcp backend, to talk to the visualizer\n",
    "# zmq_url should match the output of `python run_zmq_server.py`\n",
    "vis = vis_utils.get_vis(zmq_url=\"tcp://127.0.0.1:6000\")\n",
    "vis.delete()\n",
    "\n",
    "# draws a red box in the scene\n",
    "vis_utils.show_box_test(vis)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7fe7478d",
   "metadata": {},
   "outputs": [],
   "source": [
    "with initialize(version_base=None, config_path=\"../configs\"):\n",
    "    config = compose(config_name=\"graph_default.yaml\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "642b0a25-0e88-4eac-b661-a57a74fb10fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_inputs = get_dataset_inputs_from_dataset_config(**config.data.dataset_inputs_train, split=\"train\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "938f090b-3b28-4fd6-82dc-d4b5c5917134",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ImageDataset\n",
    "image_dataset_train = instantiate_from_dict_config(config.data.image_dataset_train, **dataset_inputs.as_dict())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5d014a6b-50fa-48ab-b135-0ab2b81c7529",
   "metadata": {},
   "outputs": [],
   "source": [
    "# grab 10 images and show their frustums\n",
    "indices = random.sample(range(len(image_dataset_train)), k=10)\n",
    "for idx in indices:\n",
    "    image = image_dataset_train[idx][\"image\"]\n",
    "    camera = get_camera(dataset_inputs.intrinsics[idx], dataset_inputs.camera_to_world[idx], None)\n",
    "    pose = camera.get_camera_to_world().double().numpy()\n",
    "    K = camera.get_intrinsics_matrix().double().numpy()\n",
    "    vis_utils.draw_camera_frustum(\n",
    "        vis,\n",
    "        image=(image.double().numpy() * 255.0),\n",
    "        pose=pose,\n",
    "        K=K,\n",
    "        height=1.0,\n",
    "        name=\"{:06d}\".format(idx),\n",
    "        displayed_focal_length=0.5,\n",
    "        realistic=False,\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fd04703a-aa50-45e4-95fd-4d881ff18d61",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "estimated_time: 3.3333333333333335\n",
      "time_elapsed: 3.5769083499908447\n"
     ]
    }
   ],
   "source": [
    "# move a camera around\n",
    "num_cameras = len(dataset_inputs.intrinsics)\n",
    "intrinsics = dataset_inputs.intrinsics\n",
    "camera_to_world = dataset_inputs.camera_to_world\n",
    "idx0, idx1 = random.sample(range(num_cameras), k=2)\n",
    "camera_a = get_camera(intrinsics[idx0], camera_to_world[idx0], None)\n",
    "camera_b = get_camera(intrinsics[idx1], camera_to_world[idx1], None)\n",
    "\n",
    "num_steps = 100\n",
    "fps = 30\n",
    "estimated_time = num_steps / fps\n",
    "print(\"estimated_time:\", estimated_time)\n",
    "\n",
    "camera_path = InterpolatedCameraPath(camera_a, camera_b)\n",
    "cameras = camera_path.get_path(steps=num_steps)\n",
    "\n",
    "start = time.time()\n",
    "for camera in cameras:\n",
    "    vis_utils.set_camera(vis, camera)\n",
    "    time.sleep(1 / fps)\n",
    "time_elapsed = time.time() - start\n",
    "print(\"time_elapsed:\", time_elapsed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f1cd7183-c514-4f87-a8cc-e14228228e24",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "4a749acc7d255f078aee52e0584cc77b3cb5aaed1b3a7407ec4262c1bf6cb526"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}