Teaching 103-1100-00L

Computer Vision and Artificial Intelligence for Autonomous Cars

Autumn 2026 · ETH Zurich · 6 ECTS

About the course

This course introduces the core computer vision techniques and algorithms that autonomous cars use to perceive the semantics and geometry of their driving environment, localize themselves in it, and predict its dynamic evolution. Emphasis is placed on techniques tailored for real-world settings, such as multi-modal fusion, domain-adaptive and outlier-aware architectures, and multi-agent methods.

Lecturer
Christos Sakaridis
When
Fridays 14:15–17:00
Where
HG D 5.2

Slides, exercise sheets, recordings, and exam materials are password-protected. Access credentials are announced in the lecture and on the course forum.

ETH course catalogue Piazza forum

Lecture team

Lecturer

Teaching Assistants

Autonomous car

Lectures

Date Time Room Topic Slides Video Link
18.09.2026 14:15–17:00 HG D 5.2 Fundamentals of Autonomous Cars PDF Video Join
25.09.2026 14:15–17:00 HG D 5.2 Fundamental Computer Vision Architectures and Algorithms for Autonomous Cars PDF Video Join
02.10.2026 14:15–17:00 HG D 5.2 Fundamental Computer Vision Architectures and Algorithms (continued) PDF TBA Join
09.10.2026 14:15–17:00 HG D 5.2 Semantic Segmentation TBA TBA Join
16.10.2026 14:15–17:00 HG D 5.2 Depth Estimation TBA TBA Join
23.10.2026 14:15–17:00 HG D 5.2 Object Detection TBA TBA Join
30.10.2026 14:15–17:00 HG D 5.2 Instance Segmentation and Panoptic Segmentation TBA TBA Join
06.11.2026 14:15–17:00 HG D 5.2 Unimodal 3D Object Detection TBA TBA Join
13.11.2026 — — No lecture — CVPR conference deadline — — —
20.11.2026 14:15–17:00 HG D 5.2 3D Reconstruction and Localization TBA TBA Join
27.11.2026 14:15–17:00 HG D 5.2 Domain Adaptation TBA TBA Join
04.12.2026 14:15–17:00 HG D 5.2 Multi-modal 2D and 3D Object Detection TBA TBA Join
11.12.2026 14:15–17:00 HG D 5.2 Visual Grounding, Anomaly Segmentation and Vehicle-to-Vehicle Communication TBA TBA Join
18.12.2026 14:15–17:00 HG D 5.2 Multiple Object Tracking and Motion Prediction TBA TBA Join

Practical sessions

Date Time Room Topic Slides Video Link
02.10.2026 10:15–12:00 Online Getting Started with Python and SLURM PDF Video Join
09.10.2026 10:15–12:00 Online Project 1 Introduction: Semantic Segmentation and Depth Estimation TBA TBA Join
16.10.2026 09:15–11:00 Online Project 1: Attention Mechanisms and Transformers TBA TBA Join
23.10.2026 10:15–12:00 Online Project 1 Q&A TBA TBA Join
30.10.2026 10:15–12:00 Online Project 1 Q&A TBA TBA Join
06.11.2026 10:15–12:00 Online Project 1 Q&A TBA TBA Join
13.11.2026 10:15–12:00 Online Project 2 Introduction: 3D Detection from Point Clouds TBA TBA Join
20.11.2026 10:15–12:00 Online Project 2 Q&A TBA TBA Join
27.11.2026 10:15–12:00 Online Project 2 Q&A TBA TBA Join
04.12.2026 10:15–12:00 Online Project 2 Q&A TBA TBA Join
11.12.2026 10:15–12:00 Online Project 2 Q&A TBA TBA Join
18.12.2026 10:15–12:00 Online Project 2 Q&A TBA TBA Join

Projects

  1. Semantic segmentation and depth estimation

    Starts
    09.10.2026
    Due
    12.11.2026

    Implement and train multi-task models for dense visual perception on real-world driving data.

    Handout: TBA

  2. 3D object detection using LiDARs

    Starts
    13.11.2026
    Due
    18.12.2026

    Detect vehicles and other agents in LiDAR point clouds from a multi-modal driving dataset.

    Handout: TBA

Prerequisites

  • Linear algebra, multivariate calculus, and probability theory.
  • Basic computer vision and machine learning.
  • Programming proficiency in Python, PyTorch, scikit-learn, and scikit-image.

Exam & grading

Exam

Examiner
Christos Sakaridis
Format
Written session examination
Duration
120 minutes
Language
English
Permitted
One A4 sheet of paper and a simple non-programmable calculator.
  • Offered only in the session following the end of the course.
  • A mock exam (short version) is provided, with and without solutions.

Grading

Projects 50% · Exam 50%

  • Projects are mandatory and conducted in groups.
  • Failing the projects results in failing the final grade.
  • Students who do not pass the projects must de-register from the session exam.

Learning objectives

  • Understand the principles of visual sensors used in autonomous cars.
  • Distinguish the dominant architectural paradigms in modern visual perception models.
  • Categorize visual perception tasks and explain the algorithms that solve them.
  • Critically analyze current research in computer vision for autonomous driving.
  • Reproduce and adapt state-of-the-art methods for visual perception.
  • Independently develop new visual perception models for autonomous cars.