16-705 Fundamentals of Computer Vision

6 units, Carnegie Mellon University

This course introduces the fundamental concepts and methods of computer vision—the analysis of images to reconstruct and understand the scenes that generated them. The course emphasizes practical understanding of modern computer vision pipelines as they arise in robotics and real-world applications. Topics span low-level image processing, geometry-based 3D reconstruction methods, learning-based approaches for semantic tasks, and motion-based methods for video analysis. The course is designed to provide graduate students with a structured foundation in computer vision, enabling them to reason about representation, geometry, and inference in visual systems and to apply these ideas in robotics research. The course is intended for graduate students who want a working and conceptual understanding of computer vision methods used in robotics and embodied AI systems.

Prerequisites: none listed

Offered: Fall 2026, Spring 2026

Courseweave needs JavaScript to show sections, workloads and planning tools.