项目介绍

2026年8月27日

DTU Compute and the Pioneer Centre for Artificial Intelligence invite applications for a PhD scholarship in 3D egocentric vision and spatial AI. The successful candidate will join the research group led by Associate Professor Theodora Kontogianni in the Visual Computing Section at DTU Compute.

Our research investigates how intelligent systems can perceive, understand, and interact with the three-dimensional world. We develop methods in computer vision, machine learning, and multimodal representation learning that enable autonomous systems to reason about objects, people, actions, and environments from partial and continuously changing observations.

The PhD project will focus on learning spatial representations from egocentric visual observations. Possible research directions include multimodal 3D perception, continual and online learning, open-world scene understanding, and adaptive perception for embodied agents. The exact research direction will be developed jointly with the selected candidate based on their interests and background.

This position offers an opportunity to conduct research at the forefront of 3D computer vision and embodied AI, collaborate with leading researchers in Denmark and internationally, and contribute to publications at major computer vision, machine learning, and robotics venues.

Responsibilities and qualifications
The goal of the project is to develop learning-based methods that allow intelligent systems to understand complex three-dimensional environments from egocentric observations. A central challenge is that an embodied agent observes the world only partially and from viewpoints that change over time. The project will investigate how models can build persistent spatial representations, combine multiple sensing modalities, and adapt as new observations and objects are encountered.

You will contribute to one or more of the following research areas:

• 3D scene understanding from egocentric or first-person observations
• Multimodal learning from RGB, depth, point clouds, video, language, or other sensor inputs
• Continual, online, or open-world learning for dynamic environments
• Spatial representation learning for embodied agents
• Perception methods supporting interaction, planning, and task execution

Your primary tasks will include:

• Conducting research and developing novel methods for 3D egocentric perception and spatial AI
• Designing, implementing, and evaluating machine-learning models
• Publishing research results in leading international conferences and journals
• Collaborating with researchers at DTU, the Pioneer Centre for AI, and international partner institutions
• Contributing to the supervision of BSc and MSc student projects
• Participating in research-group activities and relevant teaching or dissemination activities

We are looking for candidates who have:

• A strong background in computer vision and machine learning
• Experience with deep-learning frameworks such as PyTorch
• Strong programming and debugging skills in Python and/or C++
• Experience using Linux and software-development tools such as Git, Conda, or Docker
• The ability to conduct independent research and collaborate effectively in an interdisciplinary environment
• Excellent written and spoken English

Experience in one or more of the following areas would be an advantage:

• 3D computer vision, point-cloud processing, or 3D reconstruction
• Video understanding, egocentric vision, or multimodal learning
• Robotics, embodied AI, or continual learning
• Publication of research in computer vision, machine learning, or robotics

You must have a two-year master’s degree (120 ECTS points) or a similar degree with an academic level equivalent to a two-year master’s degree.

Approval and Enrolment 
The scholarship for the PhD degree is subject to academic approval, and the candidate will be enrolled in one of the general degree programmes at DTU. For information about our enrolment requirements and the general planning of the PhD study programme, please see DTU’s rules for the PhD education. 

Assessment
The assessment of applicants will be carried out by an academic assessment committee chaired by Associate Professor Theodora Kontogianni.

We offer
DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and appointment terms 
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. Please see DTU’s salary structure for scientific staff: www.inside.dtu.dk/en/human-resources/during-employment/salary/salary-structures.  

The period of employment is 3 years.

Our preferred starting date is 1 November  2026 or according to mutual agreement. The position is a full-time position.

You can read more about career paths at DTU here.

Further information
Further information may be obtained from Associate Professor Theodora Kontogianni (thekon@dtu.dk) or Head of Section, Professor Anders Bjorholm Dahl (abda@dtu.dk).

You can read more at DTU Compute -Visual Computing and previous research on Personal Page and Google Scholar.

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU – Moving to Denmark. Furthermore, you have the option of joining our monthly free seminar “PhD relocation to Denmark and startup “Zoom” seminar” for all questions regarding the practical matters of moving to Denmark and working as a PhD at DTU. 

Application procedure 
Your complete online application must be submitted no later than 4 September 2026 (23:59 Danish time). 

Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link “Apply now”, fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

• A letter motivating the application (cover letter)
• Curriculum vitae 
• Grade transcripts and BSc/MSc diploma (in English) including official description of grading scale
• Name up to 2 people who may be contacted to provide reference letter (e.g. master thesis supervisor)