The course runs August–November 2025 at Pontificia Universidad Católica de Chile. There are 28 classes, meeting on Tuesdays and Thursdays. Professor: Domingo Mery.
Learning progression
The course is organized into five chapters. Each chapter builds on the previous one, moving from foundations to application to responsibility.Cap00 — General lines
Course presentation, bibliography, and exam preparation. Establishes expectations and provides the reference materials used throughout the semester.
Cap01 — Introduction
Definitions of computer vision, motivating applications, and a two-part history of the field from early perspective geometry to the deep learning era.
Cap02 — Computational geometry
The mathematical backbone of the course. Homogeneous coordinates, 2D and 3D transformations, homographies, camera calibration, RANSAC, epipolar geometry, trifocal geometry, and 3D reconstruction.
Cap03 — Deep learning
Convolutional neural networks, object detection (YOLO), facial analysis, semantic segmentation (UNet), generative adversarial networks (GANs), anomaly detection, CLIP, Transformers, Visual Transformers (ViT), and diffusion models.
Full 28-class schedule
Cap00 — General lines (Classes 1 and 28)
Cap00 — General lines (Classes 1 and 28)
| Class | Date | Topics |
|---|---|---|
| 01 | Thu 07-Aug-2025 | Course presentation, bibliography overview |
| 28 | Thu 27-Nov-2025 | Exam support — past exam questions (2023, 2024) and solutions |
Cap01 — Introduction (Classes 2–4)
Cap01 — Introduction (Classes 2–4)
| Class | Date | Topics |
|---|---|---|
| 02 | Tue 12-Aug-2025 | Definitions (CV01); History part 1 |
| 03 | Thu 14-Aug-2025 | History (cont.); vanishing points and perspective |
| 04 | Tue 19-Aug-2025 | History part 2 |
Cap02 — Computational geometry (Classes 2–11)
Cap02 — Computational geometry (Classes 2–11)
| Class | Date | Topics |
|---|---|---|
| 02 | Tue 12-Aug-2025 | Homogeneous coordinates, points, lines, planes |
| 03 | Thu 14-Aug-2025 | 2D–2D transformations, homographies; in-class exercise E01 (John Lennon) |
| 04 | Tue 19-Aug-2025 | Homographies (cont.); 3D transformations |
| 05 | Thu 21-Aug-2025 | 3D–3D and 3D–2D transformations; in-class exercise E02 (clock rectification) |
| 06 | Tue 26-Aug-2025 | Parameter estimation, calibration, RANSAC |
| 07 | Thu 28-Aug-2025 | Mosaics; SIFT features; camera calibration |
| 08 | Tue 02-Sep-2025 | 3D reconstruction; calibration (Python and MATLAB) |
| 09 | Thu 04-Sep-2025 | Epipolar geometry; in-class exercise E04 |
| 10 | Tue 09-Sep-2025 | Epipolar geometry (cont.); multiple-view X-ray applications |
| 11 | Thu 11-Sep-2025 | Trifocal geometry; chapter summary |
Cap03 — Deep learning (Classes 12–23 and 25)
Cap03 — Deep learning (Classes 12–23 and 25)
| Class | Date | Topics |
|---|---|---|
| 12 | Tue 23-Sep-2025 | Introduction to deep learning; CNNs |
| 13 | Tue 30-Sep-2025 | CNN training; in-class exercise E05 |
| 14 | Thu 02-Oct-2025 | Object detection — YOLO + tracking |
| 15 | Tue 07-Oct-2025 | YOLO (cont.); in-class exercise E06 (mask detection) |
| 16 | Thu 09-Oct-2025 | Facial analysis |
| 17 | Tue 14-Oct-2025 | Facial analysis — social; face recognition (AdaFace); in-class exercise E07 |
| 18 | Thu 23-Oct-2025 | Semantic segmentation — UNet; in-class exercise E08 |
| 19 | Tue 28-Oct-2025 | Generative adversarial networks (GANs); detection statistics |
| 20 | Thu 30-Oct-2025 | GAN in-class exercise E09; anomaly detection |
| 21 | Tue 04-Nov-2025 | CLIP |
| 22 | Thu 06-Nov-2025 | Transformers from scratch |
| 23 | Tue 11-Nov-2025 | Visual Transformers (ViT); HuggingFace; in-class exercise E10 |
| 25 | Tue 18-Nov-2025 | Stable diffusion; diffusion models |
Cap04 — Ethics & AI (Classes 24–27)
Cap04 — Ethics & AI (Classes 24–27)
| Class | Date | Topics |
|---|---|---|
| 24 | Thu 13-Nov-2025 | The good, the bad, and the ugly of AI; essay assignment T03 released |
| 25 | Tue 18-Nov-2025 | Ethical challenges in facial recognition |
| 26 | Thu 20-Nov-2025 | Federated / swarm learning; explainability; Chilean data-protection law (Ley 19628) |
| 27 | Tue 25-Nov-2025 | Bias and fairness; good practices; explainability with MinPlus; adversarial attacks; quiz E11 |
The essay assignment T03 is described on Canvas. The quiz E11 in Class 27 is also submitted via Canvas.
Grading and assignments
The course has three main assignments plus quizzes:| Item | Description |
|---|---|
| T01 | Assignment 1 — covers computational geometry (Cap02) |
| T02 | Assignment 2 — deep learning project (released Class 18, Cap03) |
| T03 | Essay — ethics and AI (released Class 24, Cap04) |
| E01–E11 | In-class exercises throughout the semester |
| Examen | Final exam — past papers from 2023 and 2024 are available for practice |
Tools and environment
The course uses two primary computing environments:- Python / Google Colab — the primary tool for all exercises and assignments. Notebooks run in the browser with free GPU access.
- MATLAB — used for selected geometry and calibration demonstrations.