Advancing 3D Computer Graphics & Vision with Generative AI and Novel 3D Representation

This PhD project aims to advance 3D computer graphics and vision by combining state-of-the-art generative models, specifically diffusion and flow-based generative models, with cutting-edge 3D representations, such as: Neural Radiance Fields and Gaussian splatting methods. It is expected to make significant contributions to the fields of visual computing, deep learning and foundation model. By pushing the boundaries of these techniques, the research could have far-reaching impacts on medical image analysis, immersive media and gaming, digital asset creation, and autonomous robotics. The project is to develop more accurate, efficient, and expressive models for 3D visual understanding and synthesis, where the following key areas will be explored: 

* 3D scene reconstruction, object generation and rendering

* Temporal dynamics for 3D animation and video generation

* 3D Robotic vision and collaborative object manipulation

* Biomedical 3D imaging and analysis for vascular diseases

You will join the Rand2AI lab (https://rand2ai.org/) at Durham Univerisity under Dr. Jingjing Deng’s supervision. The joint lab has a number of robotic arms and mobile platforms to support the robotics research. We have dedicated GPU clusters with 4 nodes (each with 4 x NVIDIA RTX A6000 48GB GPUs) to facilitate research on deep learning and generative AI. 

Durham University

Durham University is a world top-100 university (QS), a European top-50 university (QS), ranked the 5th in the UK (Times, 2024) and a member of the research-intensive Russell Group of UK universities, focussing on research excellence delivered by world-leading academics. Durham is the third oldest university in England, following Oxford and Cambridge, founded in 1832 and situated in the ancient City of Durham, a relatively small city by international standards (pop. ~50,000) situated in the North East of England with long-established historical roots (including an on-campus UNESCO world heritage site comprising Durham Cathedral and Castle). Today the university offers a strong and unique collegiate student experience, with each student being a member of one of the university’s 17 constituent colleges, with a relatively low cost of living compared to other parts of the UK. Durham University hosts the UK regional supercomputer, Bede (128 NVIDIA V100 GPUs) which complements our departmental NVIDIA CUDA Compute Cluster (80+ GPUs up to NVIDIA A100).

Entry Requirements

* First class honours (or high 2.1 at undergraduate or equivalent Masters) degree in an Engineering, Physics, Maths or Computer Science based subject (internationally: GPA 3.3+ or equiv).

* Strong understanding of computing/engineering applications and mathematical problem solving.

* Knowledge of modern programming languages (ideally including one of Python, C++/C or Rust).

* Excellent written and spoken communication skills in English, meet the Durham University English language requirements https://www.dur.ac.uk/study/international/entry-requirements/english-language-requirements/.

* Prior experience in research, industry and/or AI based research topics is beneficial but not essential.

How to Apply

This is primarily a self-funded PhD position and applications are welcome all year round with flexibility on start date. Whilst Durham University provides fully-funded, highly competitive scholarships for exceptional PhD candidates (including DDS, DTP and CSC), the availability of these scholarships is limited and they are awarded on a merit basis each year to our top applicants across all subjects/faculties. For this project, students of exceptional quality may consider applying for the scholarships with support from the supervisor. 

Please send an email with your CV, degree transcripts and any supporting documents (ideally with a research proposal) to Dr. Jingjing Deng ([email protected]) for an initial pre-application discussion.