The University of Texas at Austin
|
Computer Science 395T
|
|
This course will cover a broad range of topics in the general area of 3D Vision and 3D Geometry Processing, ranging from 1) reconstructing 3D models from images and depth scans, 2) 3D representations (e.g., for neural networks), and 3) analysis and processing of 3D models. An unique characteristics of this course is that we will install the basic theory of numerical optimization throughout. The course is a graduate-level course that combines instruction of basic material, written homeworks , and a final project. The course targets for students who will conduct research in Graphics, Vision, Robotics, and Computational Biology .Grading is based on homeworks (70%) and the final project (30%).
Prereqs: The course assumes a good knowledge of linear algebra and probability. Please talk to me or email me if you are unsure if the course is a good match for your background.
Textbooks (Not Required but Recommended):
|
|
|
|
Date | Topics | Reading | Notes |
August 29th | (A): Introduction | ||
September 5th | (T): Math Review (Linear Algebra, Rotation, Quaternion) | Rotation Quaternion | Homework 1 |
September 10th | (T): Fundamentals of Unconstrained Optimization | Chapter 2 of [NW] | |
September 12th | (T): Fundamentals of Constrained Optimization | Chapter 12 of [NW] | |
September 17th | (A): Image Formation | Chapter 3 of [MKSS] | |
September 19th | (A): Image Primitives and Correspondence | Chapter 4 of [MKSS] | |
September 24th | (A): Reconstruction from Two Calibrated Views | Chapter 5 of [MKSS] | |
September 26th | (A): Camera Calibration and Self-Calibration | Chapter 6 of [MKSS] | |
October 1th | (A): Introduction to Multiple View Reconstruction | Chapter 7 of [MKSS] | Homework 1 due. Homework 2 out. |
October 3th | (T): Line Search Techniques | Chapter 3 of [NW] | |
October 8th | (T): Trust Region Methods | Chapter 4 of [NW] | |
October 10th | (A): Image Matching and Bundle Adjustment | Chapter 14.3-14.4 of [MKSS] | |
October 15th | (A): Optimization for SLAM | ||
October 17th | (A): Multi-View Stereo | Chapter 14.5 of [MKSS] | Homework 2 due. Homework 3 out. |
October 22th | (T): Linear Programming (Simplex method) | Chapter 13 of [NW] | |
October 24th | (T): Linear Programming (Interior-point method) | Chapter 14 of [NW] | |
October 29th | (T): Proximal Gradient Methods | Proximal Gradient Method | |
October 31th | (A): 3D Representation I (Pointcloud and Implicit) | Chapter 1-2 of [GP] | Homework 3 due. Homework 4 out. |
November 5th | (A): 3D Representation II (Triangular Mesh) | Chapter 1-2 and Chapter 7 of [BKPAL] | |
November 7th | (A): 3D Representation III (Parametric) | ||
November 12th | (A): RGBD-Based 3D Reconstruction (Data-Driven) | ||
November 14th | (A): RGBD-Based 3D Reconstruction (ICP) | ||
November 19th | (A): 3D Deep Learning I | Homework 4 due. Homework 5 out. | |
November 26th | (A): 3D Deep Learning II | ||
November 28th | (A): Map Synchronization I | ||
December 3th | (T): Map Synchronization II | SDP, ADMM-SDP | |
December 5th | (T): Map Synchronization III | Homework 5 due. | |
December 10th | Final Project Presentations | Final project report due. |