본문 바로가기 사이드메뉴 바로가기 대메뉴 바로가기

Computer Science

Courses

Introduction to Computer Vision
Text code : CSE527 / Credit : 3
  • Prerequisites Limited to CSE graduate students; others, permission of instructor
  • Textbook information Multiple view geometry in computer vision by Hartley, R., & Zisserman, A., Cambridge university press, 2003. Computer vision: algorithms and applications by Szeliski, R., & Zisserman, A., Springer Nature, 2022.

Course Coordinator Francois Rameau
Description

This course provides an in-depth exploration of 3D Computer Vision, covering the theoretical foundations of perspective geometry and their applications in deep learningbased navigation and reconstruction. Topics include image formation, neural networks for image processing, 3D reconstruction methods such as odometry, NeRF, and Gaussian Splatting, as well as object detection. This class is designed for anyone interested in reconstructing the 3D structure of a scene using images. The evaluation consists of two exams and a project of the student’s choice, offering hands-on experience and practical skills in computer vision engineering.

Prerequisite Limited to CSE graduate students; others, permission of instructor
Credits 3 Credits, Letter graded
Course Outcomes
  • Understand the theoretical foundations of projective geometry and image formation.
  • Apply traditional and deep learning methods for various problems such as keypoint detection, segmentation, and object detection.
  • Reconstruct 3D scenes using multiview geometry and deep-learning-based approaches like NeRF.
  • Develop practical skills in computer vision engineering through a hands-on project.
Textbook Multiple view geometry in computer vision by Hartley, R., & Zisserman, A., Cambridge university press, 2003.
Computer vision: algorithms and applications by Szeliski, R., & Zisserman, A., Springer Nature, 2022.
Course Webpage

 

No content has been registered.