Deep Learning for 3D Human Understanding

Understanding 3D humans is important to human machine interaction and applications like VR/AR. This project aims to develop effective and robust deep learning methods for 3D human understanding such as modelling, prediction, reconstruction and generation.

About the Supervisor

Dr. Chen’s research field is computer vision and machine learning. He has worked with several PhD students, has a track record of published works on hashing learning, object detection and 3D human in top conferences and journals and was the recipient of ICME 2018 Best Paper Award and the Doctoral Dissertation Award from China Society of Image and Graphics in 2019.

Project Description

The recent advances in deep learning has enabled many applications related to human understanding. This project focuses on deep learning algorithms to understand 3D human information from signals including images, videos, point clouds, meshes or other 3D representations by recognition, prediction and reconstruction. Related work includes using Convolutional Neural Networks or Transformers to reconstruct 3D shapes from 2D images/ estimate human pose/ recognise human-object interaction and employing Graph Convolutional Neural networks, point cloud models or implicit functions for 3D shape generation. Effective data modelling and understanding will enable applications such as action recognition/prediction, behaviour/expression analysis, 3D reconstruction/generation. The project details will be developed during the initial stage of the PhD study depending on the skillset of the applicant.

Informal enquiries about the research or project should be directed to Dr Chen indicating your areas of interest and including your CV with qualification details (copies of transcripts and certificates).

About the Department

99 percent of our research is rated in the highest two categories in the REF 2021, meaning it is classed as world-leading or internationally excellent. We are rated as 8th nationally for the quality of our research environment, showing that the Department of Computer Science is a vibrant and progressive place to undertake research. Our Machine Learning group explores and develops the capacity for algorithms to learn and make decisions and predictions from their environment.

Entry Requirements

The candidate should ideally have a good first degree or a master degree in Computer Science, Applied Mathematics or Electrical Engineering; solid mathematical background and programming skills; fluency in English language; preferably, prior experience in computer vision, machine learning and deep learning.

If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0 in each component.

How to Apply

To apply for a PhD studentship, applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form. Make sure you name Dr Zhixiang Chen as your proposed supervisor.

Information on what documents are required and a link to the application form can be found here - https://www.sheffield.ac.uk/postgraduate/phd/apply/applying 

The form has comprehensive instructions for you to follow, and pop-up help is available.

Your research proposal should:

-be no longer than 4 A4 pages, include references

-outline your reasons for applying for this studentship

-explain how you would approach the research, including details of your skills and experience in the topic area