校際選修

115-1 選課時程

進行中

  • 初選第一階段 6/15/2026
  • 初選第二階段 6/22/2026
  • 校際選修 8/24/2026
  • 初選第三階段 8/31/2026
  • 開學後加退選 9/7/2026
  • 逾期加退選 9/21/2026
選課資源

三維機器學習

Machine Learning for 3D Data

學期
109-2
學分
3 學分
當期課號
5247
永久課號
IOG5030
開課單位
智慧科學暨綠能學院
授課教師
彭其瀚
校區
歸仁
類別
選修
上課時間表
週一
5
13:20–14:10
三維機器學習
CM216
3 節連堂
6
14:20–15:10
7
15:30–16:20

* 根據陽明交大上課時間表所列

概述

This course will cover important, fundamental topics in computer graphics and computer vision that are related to 3D data and geometric models, including: 1) Stereo/multi-view geometry. 3D-to-2D Projections. 3) Optimization, especially topics related to visual computing. 3) Point cloud reconstruction (e.g., triangulation), registration, and processing. 4) Geometric processing - mesh simplification, filtering/fairing, remeshing, parameterization, etc. 5) Latest, state-of-art research in visual computing, including but not limited to Deep Learning/AI. The goal of this course is to equip students with solid understanding and hand-on experiences in visual computing (computer graphics and computer vision), especially knowledge/skill about processing 3D data and geometric models. We are in the advent of "native 3D computing" - all visual data that were previously 2D - pictures, photos, videos, etc., are increasing becoming 3D natively thanks to the advances in modern optical hardware. Students and practitioners are best equipped with knowledge and skills to understand, process, and leverage such data. Programming projects will be done in C/C++ mostly. We will implement some fun (and a bit challenging) projects about multi-view geometry and projections, 3D point cloud registration, triangulation, and geometric processing. There will be a mid-term exam and a final exam. Exams are "open-computer", which mean that students will bring their laptops (with internet connections) and do the exams. *Holiday policy: the course (at Monday afternoon) will overlap with several national holidays. At holidays we will watch full-length online lectures (e.g., on YouTube) that covers various topics in Deep Learning, Computer Vision, and Computer Graphics. Homeworks/exams may cover topics in these online lectures.

先修科目

基本C/C++程式能力. 基本數學觀念(線性代數,初淺的微積分,離散數學等) ---- Basic C/C++ programming skills. Basic mathematics such as basic Linear Algebra, Calculous, and Discrete Mathematics.

教學方式

All materials are in English (slides, homeworks, assignments, exams). Lectures are given in Chinese.

評分方式

Several homeworks. Several programming assignments. A mid-term exam and a final exam. Exams are "open-computer", which mean that students will bring their laptops (with internet connections) and do the exams.

週次計畫
週次主題
第 1 週Course introduction and overview.
第 2 週(National holiday) Online lecture watching.
第 3 週3D geometry in computer vision I: camera and projection models.
第 4 週3D geometry in computer vision II: Epipolar and multi-view geometry.
第 5 週Optimization for visual computing - an introduction.
第 6 週Point clouds I: Point cloud capturing methods and surface reconstruction.
第 7 週(National holiday) Online lecture watching.
第 8 週Mid-term exam.
第 9 週Point clouds II: registration and other topics.
第 10 週Geometry in Computer Graphics I: Mesh fairing and simplification.
第 11 週Geometry in Computer Graphics II: Introduction to 3D discrete differential geometry (DDG).
第 12 週Geometry in Computer Graphics III: Parameterization and remeshing.
第 13 週Geometry in Computer Graphics IV: Rapid 3D content generation methods - procedural modeling, geometric tiling, etc.
第 14 週Advanced optimization topics in visual computing: ODE, PDE, Monde Carlo, Markov chain Monte Carlo (MCMC), etc.
第 15 週Latest trends in visual computing research and practices: deep learning, datasets, and beyond.
第 16 週Final exam.
第 17 週National holiday. No class today.
第 18 週TBA: guest speaker.
教科書

Stanford Computer Vision course (by Prof. Fei-Fei Li and others), chapter 5-10. Computer Graphics course, CMU. http://15462.courses.cs.cmu.edu/fall2019/ Polygon Mesh Processing by Botsh et al.

Office Hours
地點
奇美樓517.
時間
Physical office hours: every Wednesday afternoon. Email communications are welcome all the time.
聯絡方式
pengchihan@nctu.edu.tw