numpySTL.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "mount_file_id": "1DVUESPEyG82w1OSw1KBsn-b9a-rAwX_v",
      "authorship_tag": "ABX9TyOOAGlnzLSje0dL0zRh8NHn",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/tiwylli/pytorch-3d-point-cloud-generation/blob/master/numpySTL.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sWcgasnOVRE2",
        "outputId": "97ec8f4c-fdc8-4416-d62a-f506c669bf1d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting numpy-stl\n",
            "  Downloading numpy_stl-3.1.1-py3-none-any.whl (20 kB)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from numpy-stl) (1.23.5)\n",
            "Requirement already satisfied: python-utils>=3.4.5 in /usr/local/lib/python3.10/dist-packages (from numpy-stl) (3.8.2)\n",
            "Requirement already satisfied: typing-extensions>3.10.0.2 in /usr/local/lib/python3.10/dist-packages (from python-utils>=3.4.5->numpy-stl) (4.9.0)\n",
            "Installing collected packages: numpy-stl\n",
            "Successfully installed numpy-stl-3.1.1\n"
          ]
        }
      ],
      "source": [
        "!pip3 install numpy-stl"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from stl import mesh\n",
        "\n",
        "# Define the 8 vertices of the cube*\n",
        "vertices = np.array([\\\n",
        "    [-1, -1, -1],\n",
        "    [+1, -1, -1],\n",
        "    [+1, +1, -1],\n",
        "    [-1, +1, -1],\n",
        "    [-1, -1, +1],\n",
        "    [+1, -1, +1],\n",
        "    [+1, +1, +1],\n",
        "    [-1, +1, +1]])\n",
        "# Define the 12 triangles composing the cube*\n",
        "faces = np.array([\\\n",
        "    [0,3,1],\n",
        "    [1,3,2],\n",
        "    [0,4,7],\n",
        "    [0,7,3],\n",
        "    [4,5,6],\n",
        "    [4,6,7],\n",
        "    [5,1,2],\n",
        "    [5,2,6],\n",
        "    [2,3,6],\n",
        "    [3,7,6],\n",
        "    [0,1,5],\n",
        "    [0,5,4]])\n",
        "\n",
        "# Create the mesh*\n",
        "cube = mesh.Mesh(np.zeros(faces.shape[0], dtype=mesh.Mesh.dtype))\n",
        "for i, f in enumerate(faces):\n",
        "    for j in range(3):\n",
        "        print(vertices[f[j],:])\n",
        "        cube.vectors[i][j] = vertices[f[j]]\n",
        "\n",
        "# Write the mesh to file \"cube.stl\"*\n",
        "cube.save('cube.stl')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5cTuIwH7VudU",
        "outputId": "250c7d33-c249-42b1-950e-123a8b48ed5b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[-1 -1 -1]\n",
            "[-1  1 -1]\n",
            "[ 1 -1 -1]\n",
            "[ 1 -1 -1]\n",
            "[-1  1 -1]\n",
            "[ 1  1 -1]\n",
            "[-1 -1 -1]\n",
            "[-1 -1  1]\n",
            "[-1  1  1]\n",
            "[-1 -1 -1]\n",
            "[-1  1  1]\n",
            "[-1  1 -1]\n",
            "[-1 -1  1]\n",
            "[ 1 -1  1]\n",
            "[1 1 1]\n",
            "[-1 -1  1]\n",
            "[1 1 1]\n",
            "[-1  1  1]\n",
            "[ 1 -1  1]\n",
            "[ 1 -1 -1]\n",
            "[ 1  1 -1]\n",
            "[ 1 -1  1]\n",
            "[ 1  1 -1]\n",
            "[1 1 1]\n",
            "[ 1  1 -1]\n",
            "[-1  1 -1]\n",
            "[1 1 1]\n",
            "[-1  1 -1]\n",
            "[-1  1  1]\n",
            "[1 1 1]\n",
            "[-1 -1 -1]\n",
            "[ 1 -1 -1]\n",
            "[ 1 -1  1]\n",
            "[-1 -1 -1]\n",
            "[ 1 -1  1]\n",
            "[-1 -1  1]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from PIL import Image\n",
        "import matplotlib.pyplot as plt\n",
        "im = Image.open(\"/content/chair.png\")\n",
        "plt.imshow(im)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 325
        },
        "id": "EtmLO7vNemVm",
        "outputId": "1d3673be-2883-47c9-d3ec-8475ac386590"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.image.AxesImage at 0x789df102e200>"
            ]
          },
          "metadata": {},
          "execution_count": 8
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "grey_img = Image.open(\"/content/chair.png\").convert('LA')\n",
        "plt.imshow(grey_img)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 325
        },
        "id": "SAy0X_JdgTpv",
        "outputId": "003a9a2c-14cd-4358-e8d4-9bd4be5903bd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.image.AxesImage at 0x789df0ef6140>"
            ]
          },
          "metadata": {},
          "execution_count": 10
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from stl import mesh\n",
        "# Define the 8 vertices of the cube\n",
        "vertices = np.array([[-1, -1, -1], [+1, -1, -1], [+1, +1, -1], [-1, +1, -1]])\n",
        "# Define the 12 triangles composing the cube\n",
        "faces = np.array([[1,2,3], [3,1,0] ])\n",
        "# Create the mesh\n",
        "cube = mesh.Mesh(np.zeros(faces.shape[0], dtype=mesh.Mesh.dtype))\n",
        "for i, f in enumerate(faces):\n",
        "  for j in range(3):\n",
        "    cube.vectors[i][j] = vertices[f[j],:]\n",
        "# Write the mesh to file \"cube.stl\"\n",
        "cube.save('surface.stl')"
      ],
      "metadata": {
        "id": "_SL3GN0HgiNm"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "Zuw7jOVliBVN"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "image_name = 'tofu.jpg'\n",
        "grey_img = Image.open('/content/'+image_name).convert('L')\n",
        "max_size=(500,500)\n",
        "max_height=50\n",
        "min_height=0\n",
        "#height=0 for minPix\n",
        "#height=maxHeight for maxPIx\n",
        "grey_img.thumbnail(max_size)\n",
        "imageNp = np.array(grey_img)\n",
        "maxPix=imageNp.max()\n",
        "minPix=imageNp.min()\n",
        "print(imageNp)\n",
        "(ncols,nrows)=grey_img.size\n",
        "\n",
        "vertices=np.zeros((nrows,ncols,3))\n",
        "\n",
        "for x in range(0, ncols):\n",
        "  for y in range(0, nrows):\n",
        "    pixelIntensity = imageNp[y][x]\n",
        "    if pixelIntensity < 255:\n",
        "      z = (pixelIntensity * max_height) / maxPix\n",
        "    else :\n",
        "      z = 0\n",
        "    #print(imageNp[y][x])\n",
        "    vertices[y][x]=(x, y, z)\n",
        "\n",
        "faces=[]\n",
        "\n",
        "for x in range(0, ncols - 1):\n",
        "  for y in range(0, nrows - 1):\n",
        "    z=0\n",
        "    # create face 1\n",
        "    vertice1 = vertices[y][x]\n",
        "    vertice2 = vertices[y+1][x]\n",
        "    vertice3 = vertices[y+1][x+1]\n",
        "    face1 = np.array([vertice1,vertice2,vertice3])\n",
        "\n",
        "    # create face 2\n",
        "    vertice1 = vertices[y][x]\n",
        "    vertice2 = vertices[y][x+1]\n",
        "    vertice3 = vertices[y+1][x+1]\n",
        "    face2 = np.array([vertice1,vertice2,vertice3])\n",
        "\n",
        "    faces.append(face1)\n",
        "    faces.append(face2)\n",
        "\n",
        "print(f\"number of faces: {len(faces)}\")\n",
        "facesNp = np.array(faces)\n",
        "# Create the mesh\n",
        "surface = mesh.Mesh(np.zeros(facesNp.shape[0], dtype=mesh.Mesh.dtype))\n",
        "for i, f in enumerate(faces):\n",
        "  for j in range(3):\n",
        "    surface.vectors[i][j] = facesNp[i][j]\n",
        "# Write the mesh to file \"cube.stl\"\n",
        "surface.save(image_name+'.stl')\n",
        "print(surface)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gQkUs4WMiN4Q",
        "outputId": "4b72504d-9218-44c9-e03e-e3f3e48291ec"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[[ 82  78  73 ... 221 221 221]\n",
            " [ 80  76  72 ... 221 221 220]\n",
            " [ 80  75  71 ... 220 220 219]\n",
            " ...\n",
            " [134 130 131 ... 122 121 121]\n",
            " [133 129 131 ... 120 124 125]\n",
            " [132 131 131 ... 123 125 127]]\n",
            "number of faces: 462074\n",
            "<Mesh: '' 462074 vertices>\n"
          ]
        }
      ]
    }
  ]
}