The Course is part of the graduate program on Visual Computing at
IMPA. It is a regular course for the master program, and it is also
recommendend for first year PhD students of the program.
The course is divided into fundamentals and trends.
The fundamental part encompasses basic concepts of the area while the trends part addresses recent developments.
Under this methodology, the basic material does not change, but each edition of the course focuses on a research theme of interest (see previous offerings below).
- Knowledge of Algorithm & Programming (C, C++, Java, etc.);
- Linear Algebra and Calculus;
- Basic knowledge about graphics and imaging;
- Signal Processing Basics
- Continuous and Discrete Fourier Transform
- Shannon Sampling Theory
- Color Fundamentals
- Digital Image
- Image Representation and Reconstruction
- Multiscale Representations and Wavelets
- Computer Vision / Image Analysis
- Machine Learning / Convolutional Neural Networks
- Video Understanding
These topics are in general covered in short seminars, with the students, in the final part of the course:
- Scene Understanding
- 3D Reconstruction from Images
- Tracking and Pose Detection
- Segmentation and Localization
- Image based Rendering
The course covers chapters 1 to 7 of the book
- J. Gomes & L. Velho, Image Processing for Computer Graphics, Springer-Verlag, 1997.
The book site contains additional material about the topics covered on the course, as
well as, exercises for each of the chapters.
Additional references for the course :
- Computer Vision: Algorithms and Applications, Rchard Szeliski
- Deep Learning, an Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press
Current offering of this course
Besides the regular course exercises and tests, the course evaluation uses the student
seminars based on additional topics, and a final project. This link contains additional
Information and material of some of the courses that we have already taught.
2020: Projects - Deep Video
2019: Projects - 3D reconstruction
2018: Projects - Generative Models
2017: Presentations - CNN
2016: Presentations - Deep Learning
2015: projects - RGB-D / Mobile
2014: projects - Omnidirectional Imaging
2013: projects - Mobile Computational Photography
2012: projects - Mobile Applications
2011: projects - RGB-D Video
2010: projects - Computational Photography II
2009: projects - Gigapixel Images
2008: projects - Image Collections
2007: projects - Statistical Image Models
2006: projects - Computational Photograpy I
2005: projects - Vision and Graphics
2003: projects - SIGGRAPH Trends
2002: projects - Color, Etc
2001: projects - Artistic Image Generation
2000 : projects - Dithering
1998 : "Image Mosaics"
1998 : "Query by Image"
1997 : "Impressionist Filtering"
Main Page | E-mail