Skip to content

CS479: Machine Learning for 3D Data

Minhyuk Sung, KAIST, Spring 2025


Teaser1

Time & Location

Time: Mon/Wed 1:00 p.m. - 2:15 p.m. (KST)
Location: Zoom / N1 Rm 201

Zoom Link

Description

3D Data are widely used in many applications in computer vision, computer graphics, and robotic, such as autonomous driving, AI-assisted 3D object/scene design, augmented reality, and physical robot interaction. Along with the recent increasing demands on processing and analyzing such 3D data, there has been tremendous progress in developing novel technologies, especially based on deep learning. In this course, we will cover the recent advances in machine learning techniques for 3D data and also discuss the remaining challenges.

Prerequisites

This course is intended for undergraduate/master students who have a basic background in deep learning and experience with PyTorch.

Course Staff

Instructor: Minhyuk Sung (mhsung@kaist.ac.kr)

Course Assistants:

Past Years

Grading

AI Coding Assistant Tool Policy

You are allowed (and even encouraged) to utilize AI coding assistant tools, such as ChatGPT, Copilot, Codex, and Code Intelligence, for your programming assignments and projects. Utilizing AI coding assistant tools will not be deemed as plagiarism. However, it is still strictly prohibited to directly copy code from the Internet or from someone else. Doing so will lead to a score of zero and a report to the university.

Important Dates

ALL ASSIGNMENTS ARE DUE 23:59 KST. (Subject to Change)

  • Assignment 1 Submission Due: April 1 (Tuesday), 23:59 KST April 8 (Tuesday), 23:59 KST April 9 (Wednesday), 23:59 KST
  • 3D Rendering Contest Sign-Up Due: April 6 (Sunday), 23:59 KST April 8 (Tuesday), 23:59 KST
  • Assignment 2 Submission Due: April 27 (Sunday), 23:59 KST
  • Assignment 3 Submission Due: May 20 (Tuesday), 23:59 KST
  • Assignment 4 Submission Due: June 10 (Tuesday), 23:59 KST
  • 3D Rendering Contest Submission Due: May 31 (Saturday), 23:59 KST

Schedule

(Subject to Change)

Week Mon Topic Wed Topic
1 Feb 24 Course Introduction
Slides		 Feb 26 3D Representations
Slides
Recording
2 Mar 3 No Class (Substitute Holiday for
the Independence Movement Day)		 Mar 5 Point Clouds 1
Slides
Recording
3 Mar 10 Point Clouds 2
Slides
Recording		 Mar 12 Assignment 1 Session:
PointNet
Slides
4 Mar 17 Implicit Neural Representations
Slides
Recording		 Mar 19 Image-to-3D 1:
Camera Model
Slides
Recording
5 Mar 24 Image-to-3D 2
Epipolar Geometry
Slides
Recording		 Mar 26 Neural Radiance Fields (NeRF)
Slides
Recording
6 Mar 31 Hybrid Representations
Slides
Recording		 Apr 2 Assignment 2 Session:
NeRF
Slides
7 Apr 7 Gaussian Splatting
Slides
Recording		 Apr 9 Midterm Summary
8 Apr 14 Midterm Apr 16 No Class (Midterm Week)
9 Apr 21 Guest Lecture 1:
Jiahui Huang
Recording		 Apr 23 Demo Session:
NeRFStudio
Slides
10 Apr 28 Assignment 3 Session:
Gaussian Splatting
Slides		 Apr 30 Guest Lecture 2
11 May 5 No Class (Children’s Day) May 7 Meshes 1
12 May 12 Meshes 2 May 14 No Class (Break)
13 May 20 Guest Lecture 3
Mar 20 (Tue) 4:00 p.m.		 May 21 Assignment 4 Session:
Marching Squares
14 May 26 Deformation May 28 3D Geneneration and More
15 Jun 2 Project Presentations 1 Jun 4 Project Presentations 2
16 Jun 9 No Class (Final Week) Jun 11 No Class (Final Week)

  1. Teaser image credits (from left to right):
    Mildenhall et al., NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, ECCV 2020.
    https://huggingface.co/blog/gaussian-splatting
    Hwang and Sung, Occupancy-Based Dual Contouring, SIGGRAPH Asia 2024.
     ↩