The Computer Vision Research Group is dedicated to pushing the boundaries of computer vision, computer graphics, animation, and complex systems simulation through groundbreaking research.
In computer vision research, our research covers open-world deep learning to solve the lack of labelled training data via self-supervised learning, few/zero-shot learning, and the shortage of computing resources on embedded devices like mobile via compressing and accelerating deep models. We also develop novel methods for visual search and object detection and modelling.
In computer graphics and animation, our research work includes simulating the human face and the production of interactive experiences in augmented and virtual reality. In simulation, we utilize graphics hardware (GPUs) to provide scalable software solutions for science and engineering problems, for example simulating pedestrians and traffic in a city area. Our work has produced FlameGPU for agent-based modelling.
visual retrieval at large scale for images and videos;
2D and 3D object detection with images;
human pose understanding including the modeling of human body, face and hands;
object and action recognition model trained on a self-supervised framework for real-world applications, including video surveillance, smart manufacturing, and health monitoring;
computer facial modelling and animation, including applications in audiovisual training, sketch-based approaches for modelling, and both geometric and physically-based animation approaches;
digital heritage, including immersive experiences (using AR and VR) and capture and processing of 3D data for the production of archaeological artifacts and spaces;
complex systems simulation, including biological cellular systems, pedestrians and transport simulation, allied with interactive visualisation;
high performance and real time computing, application of GPUs and heterogeneous architectures;
research software engineering for GPU computing and interdisciplinary application of simulation and visual computing.
- Professor Jungong Han (Head of Group)
- Dr Steve Maddock (AI for Education Lead)
- Professor Paul Richmond (EPSRC RSE Fellow)
- Dr Zhixiang Chen
- Dr Chen Chen
- Dr Jefersson A. dos Santos
- Robert Chisholm (RSE)
- Twin Karmakharm (RSE)
- Peter Heywood (RSE)
- Marwan Taher
- Research students
- Fatimah Alzahrani (Lead supervisor: Christensen, Speech and Hearing)
- John Charlton
- Yunus Cogurcu
- Rob Dennison
- Eleftherios Ioannou
- Blayze Millward (Lead supervisor: Mangan, Machine Learning and Robotics)
- James Pyle
The research group is housed in a dedicated research lab, with individual computing equipment supplied for each research student and project.
The University’s four flagship institutes bring together our key strengths to tackle global issues, turning interdisciplinary and translational research into real-world solutions.