Programplaner og emneplaner - Student
ACIT4030 Machine Learning for 3D Computer Vision Course description
- Course name in Norwegian
- Machine Learning for 3D Computer Vision
- Study programme
-
Master's Programme in Applied Computer and Information Technology
- Weight
- 10.0 ECTS
- Year of study
- 2022/2023
- Curriculum
-
FALL 2022
- Schedule
- Programme description
- Course history
-
Introduction
This course will present the state of the art in algorithms for machine learning on images and 3D data. After a brief introduction to 3D geometry, we will cover topics related to deep learning for 3D data. We will in particular study deep neural architectures for 3D data such as point clouds, images, and shape graphs.The course covers applications like classification, segmentation, shape retrieval and correspondence detection. Recent work on shape synthesis and joint embedding will also be discussed.
Recommended preliminary courses
A background in programming, machine learning, and linear algebra is an advantage. Knowledge of computer graphics and image processing is preferable, but not strictly required.
Required preliminary courses
No requirements over and above the admission requirements.
Learning outcomes
Upon successful completion of the course, the candidate:
Knowledge
- has knowledge of problems within graphics and imaging that are applicable to machine learning, such as classification, segmentation, correspondence detection, and shape retrieval.
- has a good understanding of problems related to shape synthesis.
Skills
- is able to apply state-of-the art machine learning algorithms to real-world problems related to imaging and 3D graphics.
Competence
- is aware of the state of the art in algorithms for machine learning on 3D data.
- has experience with real world problems within the course domain, with a focus on solutions using deep neural architectures.
Content
- Introduction to geometric modelling
- Convolutional neural networks in 3D
- Deep learning for point clouds
- Convolutional neural networks on graphs
- 3D synthesis and analysis
- Joint embedding for images and 3D data
Teaching and learning methods
Teaching approach is a combination of traditional weekly lectures and practical work on a semester group project. Lectures will present influential research for relevant topics. The semester group 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 ShapeNet and will have created solutions for real-world problems related to deep learning for 3D data.
Course requirements
Individual written exam, 3 hours
The exam result can be appealed.
Assessment
The final grade will be based on:
- Individual student presentation (20% of the final grade)
- One individually written evaluation of another student presentation (500-1000 words) (10% of the final grade)
- Individual final project report (between 12 500 and 17 500 words) (70% of the final grade)
All three exams must be passed in order to pass the course.
The oral examination cannot be appealed.
New/postponed exam
In case of failed exam or legal absence, the student may apply for a new or postponed exam. New or postponed exams are offered within a reasonable time span following the regular exam. The student is responsible for applying for a new/postponed exam within the time limits set by OsloMet. The Regulations for new or postponed examinations are available in Regulations relating to studies and examinations at OsloMet.
Permitted exam materials and equipment
Grade scale A-F.
Grading scale
One internal examiner. External examiners are used regularly.
Examiners
Students are required to have good programming skills, for example by having completed the course Programming.
Course contact person
Emnet er ekvivalent (overlapper 10 studiepoeng) med: DATS2500, ITPE2500
Ved praktisering av 3-gangers regelen for oppmelding til eksamen teller forsøk brukt i ekvivalente emner.