EPN-V2

ACIT4030 Machine Learning for 3D Computer Vision Emneplan

Engelsk emnenavn
Machine Learning for 3D Computer Vision
Studieprogram
Master's Programme in Applied Computer and Information Technology
Omfang
10.0 stp.
Studieår
2023/2024
Timeplan
Emnehistorikk

Innledning

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.

Anbefalte forkunnskaper

The students will work individually to complete a;task;from the available list provided in the class. The results are documented as a project report.;The total amount of text should be about 10000;+/- 2000;words, not including references and appendix with scripts etc.

The exam can 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.

Forkunnskapskrav

No formal requirements over and above the admission requirements.

Læringsutbytte

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.

Innhold

  • 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

Arbeids- og undervisningsformer

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.

Arbeidskrav og obligatoriske aktiviteter

This course has a focus on the practices and technologies used for network-based services such as large web sites and backend systems. It provides topics specific to large architectures, such as: containers, service architectures, load balancing and service continuity. In addition, topics which are relevant for working with software projects often found in this context are covered, such as release management, automated testing and agile development principles.

Vurdering og eksamen

The final grade will be based on:

  • Individual student presentation of 15 minutes (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 6000 and 11,000 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 registering 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.

Hjelpemidler ved eksamen

All aids are permitted, provided the rules for plagiarism and source referencing are complied with.

Vurderingsuttrykk

The student should have the following outcomes upon completing the course:

Knowledge

Upon successful completion of the course, the student will:

  • have advanced knowledge of service architectures and how they are applied in the industry
  • have advanced knowledge of the platforms used to deploy large-scale; services
  • have a deep understanding of the principle of service continuity and the techniques and methods used to make services scalable and robust
  • have a deep understanding of the DevOps movement and its history
  • have expert insight into release management from an operations perspective

;

Skills

Upon successful completion of the course, the student:

  • can evaluate and discuss a service architecture in relationship to;the intended service function with regard to performance, scale and robustness
  • can apply load balancing and scaling;techniques in order to create robust;services
  • can define release-management strategies
  • can evaluate and discuss a release-management plan in relationship to an agile development project

;

General competence

Upon successful completion of the course, the student:

  • can discuss;the state of agile service;management in the industry
  • can communicate challenges, analysis and conclusions in developer operations with regard to service architectures and release management to specialists as well as the general public

Sensorordning

This course uses the flipped classroom methodology to cover topics in its theoretical form as homework and let students experience them with hands-on work in the classroom. Students work individually in order to complete technical assignments. Lab-work is supervised by the teacher who provides feedback to the student along the way.;

Students will organize their work surrounding a chosen project. The project;report will based on a;task which they can choose from a list of available projects. The task will be a combination of technical work along with a theoretical discussion.

Towards the end of the course, students will spend more time on their own projects in class under continuous supervision from the course teachers. Students can use that time to discuss approaches and challenges to their own projects.;

Emneansvarlig

None