PhD Studentship: AI-based Multi-modal 3D Environment Model Reconstruction

Supervisory Team: Dr Hansung Kim

Project description:

Computer Vision is one of the most active areas where artificial intelligence (AI) is being used. This area is extremely expanding and getting a lot of interests and investments these days. Active perception of a surrounding environment through AI relies heavily on the design of architectures and their extensive training to generate compact representations. Taking advantages of recent advancements in deep learning, these representations have shown significant improvement in building new knowledge and acquiring new skills for AI agents and practical applications in our daily life.

Scene understanding studies the task of representing a captured scene in a manner emulating human-like understanding of that space. Attaining this understanding is crucial for applications such as robotics, tele-communication, smart home, healthcare and assisted living.

In this project, several PhD students are working on a pipeline for modelling and rendering of the full environment including 3D geometry, semantic objects and material attributes from multi-modal inputs such as video, audio and text. You will join this team and investigate topics in AI-based multi-modal 3D environment model reconstruction.

Supervisor

Associate Professor Hansung Kim

Vision, Learning and Control Research Group

School of Electronics and Computer Science, University of Southampton

www.3dkim.com/Eng/index.html

Start Date

You can start in Sep 2024, Jan 2025 or April 2025. But you must apply by 19 June 2024 if you want to apply for the scholarship, and should be able to start in Sep 2024.

Requirements

All applicants are required to have a first class honours degree (or equivalent) with some further requirements for non-native English speakers. Applicants without MSc or MEng in computer vision or machine learning would have to provide strong justification that they would be able to complete a PhD in this field.

Essential selection criteria include:

• Prior knowledge in computer vision and machine learning.
• Proficiency in Python

Desirable selection criteria include:

• Experience in C++
• Experience in camera or VR systems

Funding Opportunities

There is a high chance of university DTP scholarship (3.5-year full tuition fee and stipend) for a UK home student because we have 50% matched funding from our project. We also welcome self-funded international students. Other research expenses such as research equipment, travel expenses and publication expenses will be supported from the project. 

Entry Requirements

Closing date:

There is no hard deadline but you must apply by 19^th June 2024 if you want to apply for the scholarship.

Applications will be considered in the order that they are received, the position will be considered filled when a suitable candidate has been identified.

How to apply

Directly contact Dr Hansung Kim h.kim@soton.ac.uk with your CV, Degree Transcripts and brief introduction.

Dr Kim will arrange an interview and guide to the official application for successful applicants.

The official Applications should include:

• Research Proposal
• Curriculum Vitae
• Two reference letters
• Degree Transcripts/Certificates to date

For further information please contact: feps-pgr-apply@soton.ac.uk

Advert information