Get free PhD updates, every week | SIGN UP NOW Get free PhD updates, every week | SIGN UP NOW

AI-based Perception-aware Visual Contents Processing for Sustainable and Carbon-neutral Digital Economy [Self-Funded Students Only]

   Cardiff School of Computer Science & Informatics

  , Prof Paul Rosin  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Keywords: digital economy, sustainability, carbon neutrality, perception, visual contents, AI, deep learning, computer vision

Aims and Methods

The recent boom in the digital economy (e.g. Tiktok, Metaverse) raised concerns about its high energy consumption [1], which counters the global carbon neutrality discussed at the recently COP26 conference in Glasgow, UK. Furthermore, as the famous quote “over 80% of the information our brains process is visual” suggests, visual content consumes the most storage, internet traffic, and thus energy among different types of digital contents. Therefore, addressing the global climate challenge, this project aims to make digital economy sustainable and carbon-neutral by developing novel visual contents processing techniques that simultaneously maximizes their perceptual quality and minimizes their energy consumption.

To achieve such aims, this project will use the latest AI and deep learning techniques to produce compact but high-quality encodings of visual contents that reduce their storage, transmission, and thus energy consumption. Specifically, we will answer the following research questions:

  • How to assess the perceptual quality of visual contents (e.g. images, videos) under different conditions (e.g. resolutions, frame rates)? Existing approaches either use natural statistics or require expensive experiments involving human subjects to create training data [2]. Thus, both methods are only applicable to specific types of visual contents that satisfy the conditions (e.g. image resolution) implicitly encoded in the statistical value computations or training data. We will propose a new evaluation measure that can faithfully assess how good the quality of visual content is across different conditions.
  • How to optimize/process the visual contents to maximize its perceptual quality given fixed conditions? Fixed conditions (e.g. fixed screen resolution of a digital device) are common in real-world applications. We will incorporate the evaluation measure obtained above into the development of novel AI algorithms that can improve the perceptual quality of visual content for low-end but energy-efficient devices.
  • How to optimize/process the visual contents to minimize its energy consumption given fixed perceptual quality? Similar as above, by incorporating our novel evaluation measure, we will develop novel AI algorithms for high-end devices to reduce the energy consumption of their visual content without sacrificing their perceptual quality.


  • A novel evaluation measure for assessing the perceptual quality of visual content under different conditions.
  • Novel algorithms for improving the perceptual quality of visual content on low-end but energy-efficient devices.
  • Novel algorithms for reducing the energy consumption of visual content on high-end devices without sacrificing its perceptual quality.

Please contact Dr. Yipeng Qin () or Prof. Paul Rosin () for further information.

Academic criteria:

A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas. 

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component. 

How to apply:

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below

This project is accepting applications all year round, for self-funded candidates via 

In order to be considered candidates must submit the following information: 

  • Supporting statement 
  • CV 
  • In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
  • Qualification certificates and Transcripts
  • Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
  • References x 2 
  • Proof of English language (if applicable)

Interview - If the application meets the entrance requirements, you will be invited to an interview.  

If you have any additional questions or need more information, please contact:  

Funding Notes

This project is offered for self-funded students only, or those with their own sponsorship or scholarship award.
Please note that a PhD Scholarship may also available for this PhD project. If you are interested in applying for a PhD Scholarship, please search FindAPhD for this specific project title, supervisor or School within its Scholarships category.


[1] Morley, J., Widdicks, K. and Hazas, M., 2018. Digitalisation, energy and data demand: The impact of Internet traffic on overall and peak electricity consumption. Energy Research & Social Science, 38, pp.128-137.
[2] Athar, Shahrukh, and Zhou Wang. "A comprehensive performance evaluation of image quality assessment algorithms." IEEE Access 7 (2019): 140030-140070.

How good is research at Cardiff University in Computer Science and Informatics?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs