Author: Aaron

I received the B.Sc. (Hons) and M.Sc. degrees from Shanghai Jiao Tong University, Shanghai, China, in 2005 and 2008 respectively, and the Ph.D degree from University of Bristol, Bristol, United Kingdom, in 2012. I am currently working in the Visual Information Laboratory, which is led by Prof. David Bull, within the Department of Electrical and Electronic Engineering , University of Bristol, as a Research Assistant, with projects on parametric video coding and Immersive Technology Lab.

MyWorld: Visual Computing and Visual Communications Research Internships 2025

Posted on by Aaron

About

We are excited to announce that 2x funded summer internships will be available in the summer of 2025, supervised by academics at the Visual Information Lab, University of Bristol. Each intern will work full-time for 7 weeks on cutting-edge research in image and video processing, with support from senior researchers in the group.

These internship projects are supported by MyWorld, a creative technology programme in the UK’s West of England region, funded by £30 million from UK Research and Innovation’s (UKRI) Strength in Places Fund (SIPF).

Eligibility of students and Assessment

To be eligible for a summer internship, students must meet the following criteria:

  • Be a full-time student at the University of Bristol.
  • Be in their second or penultimate year of study (not in their first or final year).
  • Be able to work in person at the University of Bristol during the internship period.
  • Have a strong interest in postgraduate research, particularly in image and video technology.

In line with the University’s commitment to promoting equity and diversity, we particularly welcome and encourage applications from students whose ethnicity, gender, and/or background are currently underrepresented in our postgraduate community.

Students will be assessed on:

  • Academic record
  • Interest in postgraduate research

Project 1

Title: Implicit video compression based on generative models

Description:
This project will leverage various generative models to efficiently represent and compress standard and immersive video signals. Unlike traditional compression techniques, which rely on explicit encoding and decoding processes, this type of approach is expected to learn a compact, latent representation of video content, and then reconstruct high-quality video frames from this compressed representation. This approach aims to achieve better compression ratios while maintaining high visual fidelity, making it particularly promising for applications in video streaming, storage, and real-time communication.

Related works:
[1] Kwan, Ho Man, et al. “HiNeRV: Video compression with hierarchical encoding-based neural representation.”, NeurIPS 2023. [Paper]
[2] Gao, Ge, et al. “PNVC: Towards Practical INR-based Video Compression.”, arXiv:2409.00953, 2024. [Paper]
[3] Blattmann, Andreas, et al. “Align your latents: High-resolution video synthesis with latent diffusion models.”, CVPR 2023. [Paper]

Supervisor:
Please contact Dr. Aaron Zhang (fan.zhang@bristol.ac.uk) for any inquiries.

Project 2

Title: Zero-shot learning for video denoising

Description:
This project aims to develop video denoising through the adoption of zero-shot learning techniques, eliminating the need for conventional noisy-clean training pairs. By leveraging deep learning models that can generalise from unrelated data, the project seeks to develop an innovative denoising framework that can effectively improve video quality under a variety of conditions without prior specific examples. This approach not only promises significant advancements in video processing technology but also extends potential applications in real-time broadcasting, surveillance, and content creation, where optimal video clarity is essential.

Related works:
[1] Y. Mansour and R. Heckel, “Zero-Shot Noise2Noise: Efficient Image Denoising without any Data”, CVPR 2023. [Paper]
[2] Y. Shi, et al., “ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images”, CVPR 2024. [Paper]

Supervisor:
Please contact Dr Pui Anantrasirichai (n.anantrasirichai@bristol.ac.uk) for any inquiries.

Application

  1. Submit your [Application Form] by 31 January 2025.
  2. Shortlisted candidates will be interviewed by 14 February 2025.
  3. Successful students will be notified by 28 February 2025.
  4. Students are provided internship acceptance form to confirm information required by TSS for registration by 14 March 2025.

Payment

Students will be paid the minimum living wage for the duration of the internship (£12.21 per hour in 2025), which equates to approximately £428 (35 hours) per week before any National Insurance or income tax deductions. Please note that payment will be made a month in arrears, meaning students will be paid for the hours worked at the end of each month.

MyWorld Scholarship: Deep Video Coding

Posted on by Aaron

About the Project

Video technology is now pervasive, with mobile video, UHDTV, video conferencing, and surveillance all underpinned by efficient signal representations. As one of the most important research topics in video processing, compression is crucial in encoding high quality videos for transmission over band-limited channels.

The last three decades have seen impressive performance improvement in standardised video algorithms. The latest standard, VVC and the new royalty free codec, AOM/AV1, are expected to achieve 30-50% gains in coding performance over HEVC. However, this figure is far from satisfactory considering the large amount video data consumed every day.

Inspired by the recent breakthrough in artificial intelligence, in particular deep learning techniques developed for video processing applications, this PhD project will investigate novel deep learning-based video coding tools, network architectures and perceptual loss functions for modern codecs.

This project is funded by MyWorld UKRI Strength in Places Programme.

URL for further information: http://www.myworld-creates.com/ 

Candidate Requirements

Applicants must hold/achieve a minimum of a master’s degree (or international equivalent) in a relevant discipline. Applicants without a master’s qualification may be considered on an exceptional basis, provided they hold a first-class undergraduate degree. Please note, acceptance will also depend on evidence of readiness to pursue a research degree. 

If English is not your first language, you need to meet this profile level:

Profile E

Further information about English language requirements and profile levels.

Basic skills and knowledge required

Essential: Excellent analytical skills and experimental acumen.

Desirable: A background understanding in one or more of the following:

Video compression

Artificial intelligence / Machine Learning / Deep Learning

Application Process

  • All candidates should submit a full CV and covering letter to myworldrecruitment@myworld-creates.com (FAO: Professor David R. Bull).
  • Formal applications for PhD are not essential at this stage, but can be submitted via the University of Bristol homepage (clearly marked as MyWorld funded): https://www.bristol.ac.uk/study/postgraduate/apply/
  • A Selection Panel will be established to review all applications and to conduct interviews of short-listed candidates.
  • This post remains open until fulfilled.

For questions about eligibility and the application process please contact SCEEM Postgraduate Research Admissions sceem-pgr-admissions@bristol.ac.uk

Funding Notes

Stipend at the UKRI minimum stipend level (£16,062 p.a. in 2022/23) will also cover tuition fees at the UK student rate. Funding is subject to eligibility status and confirmation of award.


To be treated as a home student, candidates must meet one of these criteria:

  • be a UK national (meeting residency requirements)
  • have settled status
  • have pre-settled status (meeting residency requirements)
  • have indefinite leave to remain or enter.

MyWorld PhD Scholarship: Volumetric Video Compression Compression

Posted on by Aaron

About the Project

Among all video content, one of the areas that has grown significantly over recent years is based on the use of augmented and virtual reality (AR and VR) technologies. They have the potential for major growth, and developments in displays, interactive equipment, mobile networks, edge computing, and compression are likely to facilitate these in the coming years.

A key new format that underpins the development of these new technologies is referred to volumetric video, with commonly used formats including point clouds, multi-view + depth and equirectangular representations. Various volumetric video codecs have been developed to perform data compression for transmission or storage of these formats. To present/display volumetric video content, the compressed data is decoded and post-processed using synthesizer/renderer which enables 3DoF/6DoF viewing capabilities on AR or VR devices.

In this context, this 3.5 year PhD project will focus on the two essential stages within this workflow: volumetric video compression and post-processing. Inspired by recent advances in deep video compression and rendering, we will research novel AI-based production workflows for volumetric video content to significantly improve the coding efficiency and the perceptual quality of the final rendered content.

This project is funded by the MyWorld UKRI Strength in Places Programme at the University of Bristol. It fits well within one of the core research areas outlined in the MyWorld programme on video production and communications for immersive content. The student working on this project will gain experience on immersive video production workflows, from capture and contribution to live editorial production and delivery at scale to a growing variety of XR capable devices.

URL for further information: http://www.myworld-creates.com/ 

Candidate Requirements

Applicants must hold/achieve a minimum of a master’s degree (or international equivalent) in a relevant discipline. Applicants without a master’s qualification may be considered on an exceptional basis, provided they hold a first-class undergraduate degree. Please note, acceptance will also depend on evidence of readiness to pursue a research degree. 

If English is not your first language, you need to meet this profile level:

Profile E

Further information about English language requirements and profile levels.

Basic skills and knowledge required

Essential: Excellent analytical skills and experimental acumen.

Desirable: A background understanding in one or more of the following:

Video compression

3D Computer vision

Artificial intelligence / Machine Learning / Deep Learning

Application Process

  • All candidates should submit a full CV and covering letter to myworldrecruitment@myworld-creates.com (FAO: Professor David R. Bull).
  • Formal applications for PhD are not essential at this stage, but can be submitted via the University of Bristol homepage (clearly marked as MyWorld funded): https://www.bristol.ac.uk/study/postgraduate/apply/
  • A Selection Panel will be established to review all applications and to conduct interviews of short-listed candidates.
  • This post remains open until fulfilled.

For questions about eligibility and the application process please contact SCEEM Postgraduate Research Admissions sceem-pgr-admissions@bristol.ac.uk

Funding Notes

Stipend at the UKRI minimum stipend level (£16,062 p.a. in 2022/23) will also cover tuition fees at the UK student rate and an industrial top-up. Funding is subject to eligibility status and confirmation of award.
To be treated as a home student, candidates must meet one of these criteria:

  • be a UK national (meeting residency requirements)
  • have settled status
  • have pre-settled status (meeting residency requirements)
  • have indefinite leave to remain or enter.

MyWorld Postdoctoral Research Associate Posts – UKRI Strength in Places Programme

Posted on by Aaron

The Role

The newly established MyWorld research programme, led by the University of Bristol, is a flagship five-year, £46m R&D programme collaborating with numerous industrial and academic organisations. The MyWorld Creative Technologies Hub is now expanding in line with its mission to grow the West of England’s Creative Industries Cluster with major investments in new facilities and staff at all levels.

We are now offering unique opportunities for four Post-Doctoral Research Associates in

  1. AI methods for Video Post-Production
  2. Robot Vision for Creative Technologies
  3. Perceptually Optimised Video Compression (sponsored by our collaborator, Netflix, in Los Gatos, USA).
  4. Visual Communications

Contract and Salary

All these four posts are based in the Faculty of Engineering, University of Bristol, and the salary range is Grade I = £34,304 – £38,587 per annum or Grade J = £38,587 – £43,434 per annum.

Application Information

We anticipate that candidates will possess a good honours degree along with a PhD in related disciplines, or extensive relevant industrial/commercial experience. We expect a high standard of spoken and written English and the ability to work effectively both independently and as part of a team.

Please following the link provided for each post to access detailed job description and the application system.

MyWorld PhD Scholarships 2022 – UKRI Strength in Places Programme

Posted on by Aaron

Introduction

MyWorld is a £46m R&D programme, awarded to the University of Bristol, under the leadership of Professor David Bull, with £30m from the UKRI Strength in Places Fund (SIPF) and a further £16m committed from an alliance of more than 30 industry and academic organisations. SIPF is a UK Research and Innovation (UKRI) flagship competitive funding scheme that takes a place-based approach to research and innovation funding with the aim of creating significant local economic growth. It is a major intervention by UK Government to explore the potential of devolved R&D funding.

There are now a number of opportunities for outstanding candidates to join the MyWorld team as PhD students, who are expected to start from Sept 2022. Opportunities for innovation and investigation exist across the MyWorld portfolio, including content acquisition and post-production, content delivery and interactivity, and audience understanding.

Role Description

All posts will cover student stipend at a basic rate of £15,609 per annum (2022 rates) with possibility of enhancement by up by £3,000 in some cases. Fees for home (UK-based) students are covered in all cases. Several awards cover fees for EU students and some cover overseas students.

Appointees will be expected to integrate within the MyWorld team, to conduct internationally-leading research, and to contribute to the wider objectives and activities of the programme.  Many of the awards will involve collaboration with our industry partners and would offer the potential of career development through internships as part of the PhD.

Research Focus

The Visual Information Laboratory in Bristol Vision Institute (BVI) and the MyWorld Programme combine to make the University of Bristol a powerhouse for the development of visual media communications. The work of these groups in this area has been supported by world-leading organisations such as Netflix, BBC, BT, NTT and YouTube. The research focus of these PhD studentships will be linked to the strategic objectives of MyWorld, promoting new technology research that underpins the delivery of future experiences and services. Applications are invited in the following areas:

  • Content Acquisition and Post-Production: AI methods in post-production – video denoising, colorisation and enhancement; low light fusion and autofocus ; virtual production technologies; intelligent and automated cinematographies (including drone cinematography); camera tracking and SLAM methods in virtual production; Building interactive worlds – enabling the metaverse; creating re-useable assets for virtual production.
  • Content Delivery and Interactivity: perceptually optimised video compression; dynamic optimisation of streamed video; energy-efficient video coding; new architectures and tools for emerging AoM standards; machine learning methods for video delivery; perceptual video quality metrics; transcoding methods for user generated content; volumetric video coding; coding beyond compression, media network optimisation.
  • Audience Understanding: Methods for assessing quality of experience and immersion; biometrics, and fusion of these, for audience understanding; motion magnification for user engagement; creation and exploitation of visual field maps.
  • Experimental Productions: Enabling the metaverse; building environments for virtual rehearsal; building and evaluating immersive natural history experiences.

Application Procedure and Selection Process

  • All candidates should submit a full CV and covering letter to myworldrecruitment@myworld-creates.com (FAO: the contact of the research topic that you are applying for) by the deadline.
  • Formal applications for PhD are not essential at this stage, but can be submitted via the University of Bristol homepage (clearly marked as MyWorld funded):
  • A Selection Panel will be established to review all applications and to conduct interviews of short-listed candidates.
  • Candidates will be invited to give a presentation prior to their formal interview, as part of the final selection process.
  • All posts will remain open until filled.

Contact

For an informal discussion about the scholarships, please contact:

Job Description Document

Detailed role description and research topics can be found in the [JD document] and at

Learning-optimal Deep Visual Compression

Posted on by Aaron

David Bull, Fan Zhang and Paul Hill

INTRODUCTION

Deep Learning systems offer state-of-the-art performance in image analysis, outperforming conventional methods. Such systems offer huge potential across military and commercial domains including: human/target detection and recognition and spatial localization/mapping. However, heavy computational requirements limit their exploitation in surveillance applications, particularly airborne, where low-power embedded processing and limited bandwidth are common constraints.

Our aim is to explore deep learning performance whilst reducing processing and communication overheads, by developing learning-optimal compression schemes trained in conjunction with detection networks.

ACKNOWLEDGEMENT

This work has been funded by DASA Advanced Vision 2020 Programme.