ASSIGNMENT 8

In this assignment, we will create and visualize point clouds, as well as convert other object representations into point clouds. Moreover, we will train a vanilla implementation of Point Net to classify a dataset of pointclouds.

The goals of this practice are the following:

  • Visualize point clouds
  • Convert polygonal meshes into point clouds
  • Convert depth maps into point clouds
  • Generate point clouds procedurally
  • Use Point Net to classify point clouds

Instructions:

If you’re using Google Colab, you just need to have a google account and an associated Google Drive. Make a copy of the notebook located below and modify it as requested.

In case you’re choosing to work locally in your machine you must set Anaconda or a venv virtual environment, and install the necessary libraries. Create a folder in your Google Drive or in your machine’s workspace. Copy to your drive folder or download the following notebook:

Assignment 8 Notebook Open In Colab

  1. Follow the instructions in the notebook for completing the assignment.
  2. If you want, you can build auxiliary .py scripts and call them from your notebook, for organizational purposes.

Submission

The assignment is due on May 29th, 2023 at 11:59pm (GMT-3).

Students should send their assignments before the due date to hallpaz@impa.br with a copy to lvelho@impa.br. Late delivers will be consider subject to a lower score.

The submission email should be sent with the subject “Assignment 8 - [first-name] - [last-name]”. The assignment can be structured and sent in two ways:

If your whole solution is implemented in the same notebook as the one provided for the assignment, then you can send just the .ipynb file as the solution. If parts of your implementation were done in auxiliary .py scripts, then you must send both the final notebook and the scripts inside a .zip file. The organization of the code will also be considered in the evaluation.

References and other useful contents:

  1. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation - paper
  2. https://shapenet.org
  3. ShapeNet: An Information-Rich 3D Model Repository
  4. PyTorch3D source code for Meshes data structure.
  5. Objaverse
  6. Synthetic Data Generation for Machine Learning