ACIT4030 Machine Learning for 3D Computer Vision Course description

This course will present the state of the art in algorithms for machine learning on images and 3D data. After a brief introduction to image processing and 3D geometry, we will cover topics within both supervised and unsupervised learning. The course covers classical problems like classification, segmentation, and correspondence detection. Recent work on shape and image synthesis will also be discussed. We will in particular study deep neural architectures for 2D images and 3D data such as point clouds and shape graphs. Additionally, 3D shape design with generative models will be presented.

We assume good background in programming, machine learning, and linear algebra. Knowledge of computer graphics and image processing is preferable, but not strictly required.

No formal requirements over and above the admission requirements.

A student who has completed this course should have the following learning outcomes, defined in terms of knowledge, skills and general competence:

Knowledge

On successful completion of this course the student

• has advanced knowledge of cultural differences and cultural dimensions related to universal design
• has advanced knowledge of technology, best practices and development processes for ICT solutions
• has advanced knowledge of how to analyse the cultural conditions that lead to communication gaps and digital divides

Skills

On successful completion of this course the student

• can carry out necessary analysis and testing across cultures
• can design culture neutral prototypes
• can use knowledge of different cultures and group dynamics to communicate, collaborate and resolve conflicts
• can act objectively when carrying out evaluations and have knowledge about their own impact on processes and results

General competence

On successful completion of this course the student

• can analyse academic, professional and ethical issues related to accessibility in diverse cultures
• can apply knowledge and skills in universal design of ICT to solve accessibility problems in diverse cultures
• can provide comprehensive independent study and master expressions and terms in the field
• can contribute to new thinking and innovation processes

Teaching approach is a combination of traditional weekly lectures and assignments, student- led seminars, and a final project. Lectures will present the core theory of the course content and homework will focus on theoretical knowledge. In student-led seminars, topical research papers will be presented and discussed. The final project exposes the student to a chosen real- world problem relevant to the course topic.

Practical training

The student will be exposed to programming with repositories such as ImageNet and ShapeNet and will have created solutions for real-world problems related to data-driven graphics and imaging.

The course is organized as a series of lectures and seminars that cover the main theories. After this, students may travel abroad (for four to six weeks) to carry out fieldwork in collaboration with partners. The availability of partner institutions and their reseacher / supervisor to accept students may vary. Examples of possible fieldwork are requirement analysis or testing a culture neutral prototype.

• A group project plan must be approved before the project starts. Students will receive feedback during the planning stage of the project. Groups carry out projects, which last for one month, according to the approved project plan.
• A 30-minute group project presentation is to be delivered in a mini-conference in class in the end of the semester.

All aids.

For the final assessment a grading scale from A to E is used, where A denotes the highest and E the lowest pass grade, and F denotes a fail.

Two internal examiners will assess the reports and reflection statements. External examiner is used periodically.