Advancing 3D Computer Graphics & Vision with Generative AI and Novel 3D Representation University of Bristol in United Kingdom

This PhD opportunity at the University of Bristol focuses on advancing the field of 3D computer vision and graphics by integrating cutting-edge generative modelling techniques, including diffusion models and flow-based generative models, with innovative 3D scene representations such as Neural Radiance Fields (NeRF) and Gaussian Splatting (GS). The project aims to develop accurate, efficient, and expressive generative frameworks for 3D scene understanding, reconstruction, and synthesis, emphasizing scalability and real-world applicability.

Key research areas include:

• 3D Scene Reconstruction and Novel View Synthesis: Utilizing diffusion and flow-based priors to achieve robust reconstruction from sparse, noisy, or multi-modal inputs (e.g., RGB-D, multi-view video, text prompts).
• 3D Object Generation and Rendering: Creating controllable generative pipelines for producing geometry-aware and physically consistent 3D assets, with applications in gaming, digital twin creation, and content generation.
• Spatial-Temporal Modelling for 4D (Dynamic) Scenes: Extending static 3D generative models to capture temporal dynamics, enabling animation, video-driven 3D reconstruction, and generative simulation of human motion or complex interactions.
• Scalable Representations and Learning Algorithms: Investigating efficient training and inference strategies, including hierarchical representation and model distillation into compact foundation models suitable for large-scale and real-time deployment.

The research is expected to contribute to both theoretical advancements (novel architectures, representation learning, and probabilistic modelling) and practical systems that broaden the impact of generative AI for 3D understanding and synthesis. Potential applications span medical imaging (3D/4D reconstruction and analysis), immersive media and VR/AR, autonomous robotics and navigation, and digital asset generation.

The project is based in the School of Engineering Mathematics and Technology at the University of Bristol. Candidates should possess strong knowledge in mathematics, computer vision, and deep learning, along with excellent coding skills. Interested applicants are encouraged to contact Dr. Jingjing Deng ([email protected]) for further discussion and guidance on the application process.

The application deadline is May 31, 2026. For more information and to apply, visit the project page on FindAPhD.