MyWorld Postdoctoral Research Associate Posts – UKRI Strength in Places Programme

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

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 (up to 3 posts): AI methods in post-production – video denoising, colorisation and enhancement; low light fusion and autofocus (BBC iCASE sponsored); 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 (up to 3 posts): perceptually optimised video compression; dynamic optimisation of streamed video; energy-efficient video coding; new architectures and tools for emerging AoM standards (Netflix sponsored); machine learning methods for video delivery; perceptual video quality metrics; transcoding methods for user generated content; volumetric video coding (BT iCASE sponsored); coding beyond compression, media network optimisation.
  • Audience Understanding (2 posts): 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 (1 post): 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. It is expected that the shortlisting selection process will be held in week commencing April 4th 2022, with interviews to follow.
  • The initial closing date for applications is Friday April 1st 2022. The positions will however remain available until all scholarships are awarded.

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

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.

 

 

A Simulation Environment for Drone Cinematography

Fan Zhang, David Hall, Tao Xu, Stephen Boyle and David Bull

INTRODUCTION

Simulations of drone camera platforms based on actual environments have been identified as being useful for shot planning, training and re­hearsal for both single and multiple drone operations. This is particularly relevant for live events, where there is only one opportunity to get it right on the day.

In this context, we present a workflow for the simulation of drone operations exploiting realistic background environments constructed within Unreal Engine 4 (UE4). Methods for environmental image capture, 3D reconstruction (photogrammetry) and the creation of foreground assets are presented along with a flexible and user-friendly simulation interface. Given the geographical location of the selected area and the camera parameters employed, the scanning strategy and its associated flight parameters are first determined for image capture. Source imagery can be extracted from virtual globe software or obtained through aerial photography of the scene (e.g. using drones). The latter case is clearly more time consuming but can provide enhanced detail, particularly where coverage of virtual globe software is limited.

The captured images are then used to generate 3D background environment models employing photogrammetry software. The reconstructed 3D models are then imported into the simulation interface as background environment assets together with appropriate foreground object models as a basis for shot planning and rehearsal. The tool supports both free-flight and parameterisable standard shot types along with programmable scenarios associated with foreground assets and event dynamics. It also supports the exporting of flight plans. Camera shots can also be designed to pro­vide suitable coverage of any landmarks which need to appear in-shot. This simulation tool will contribute to enhanced productivity, improved safety (awareness and mitigations for crowds and buildings), improved confidence of operators and directors and ultimately enhanced quality of viewer experience.

DEMO VIDEOS

Boat.mp4

Cyclist.mp4

REFERENCES

[1] F. Zhang, D. Hall, T. Xu, S. Boyle and D. Bull, “A Simulation environment for drone cinematography”, IBC 2020.

[2] S. Boyle, M. Newton, F. Zhang and D. Bull, “Environment Capture and Simulation for UAV Cinematography Planning and Training”,  EUSIPCO, 2019

BVI-SR: A Study of Subjective Video Quality at Various Spatial Resolutions

Alex Mackin, Mariana Afonso, Fan Zhang, and David Bull

ABSTRACT

BVI-SR contains 24 unique video sequences at a range of spatial resolutions up to UHD-1 (3840p). These sequences were used as the basis for a large-scale subjective experiment exploring the relationship between visual quality and spatial resolution when using three distinct spatial adaptation filters (including a CNN-based super-resolution method). The results demonstrate that while spatial resolution has a significant impact on mean opinion scores (MOS), no significant reduction in visual quality between UHD-1 and HD resolutions for the superresolution method is reported. A selection of image quality metrics were benchmarked on the subjective evaluations, and analysis indicates that VIF offers the best performance.

SOURCE SEQUENCES

DATABASE DOWNLOAD

[DOWNLOAD] subjective data, instructions and related file.

[DOWNLOAD] all videos from University of Bristol Research Data Storage Facility.

[DOWNLOAD] all videos from MS OneDrive. Please fill a simple registration form to get access. The MS OneDrive verification code will be sent within up to 2 days after we receive the form. Please note the code may be in your Spam box.

 

If this content has been mentioned in a research publication, please give credit to the University of Bristol, by referencing the following paper:

[1] A. Mackin, M. Afonso, F. Zhang and D. Bull, “A study of subjective video quality at various spatial resolutions”, IEEE ICIP, 2018.

[2] A. Mackin, M. Afonso, F. Zhang and D. Bull,”BVI-SR Database“, 2020.

BVI-DVC: A Training Database for Deep Video Compression

Di Ma, Fan Zhang and David Bull

INTRODUCTION

Deep learning methods are increasingly being applied in the optimisation of video compression algorithms and can achieve significantly enhanced coding gains, compared to conventional approaches. Such approaches often employ Convolutional Neural Networks (CNNs) which are trained on databases with relatively limited content coverage. In this work, a new extensive and representative video database, BVI-DVC is presented for training CNN-based video compression systems, with specific emphasis on machine learning tools that enhance conventional coding architectures, including spatial resolution and bit depth up-sampling, post-processing and in-loop filtering. BVI-DVC contains 800 sequences at various spatial resolutions from 270p to 2160p and has been evaluated on ten existing network architectures for four different coding tools. Experimental results show that this database produces significant improvements in terms of coding gains over three existing (commonly used) image/video training databases under the same training and evaluation configurations. The overall additional coding improvements by using the proposed database for all tested coding modules and CNN architectures are up to 10.3% based on the assessment of PSNR and 8.1% based on VMAF.

SOURCE EXAMPLES

PERFORMANCE

This database has been compared to other three commonly used datasets for training ten popular network architectures which are employed in four different CNN-based coding modules (in the context of HEVC). The figure below shows the average coding gains in terms of BD-rates on JVET test sequences over original HEVC.

USEFUL LINKS

[DOWNLOAD] all videos from MS OneDrive. Please fill a simple registration form to get access. The MS OneDrive verification code will be sent within up to 2 days after we receive the form. Please note the code may be in your Spam box.

[DOWNLOAD] all videos from University of Bristol Research Data Storage Facility. It is also required to fill a registration form, but it could take weeks to get access.

[README] before using the database and for copyright permissions.

If there is any issue regarding this database, please contact fan.zhang@bristol.ac.uk

REFERENCE

If this content has been mentioned in a research publication, please give credit to the University of Bristol, by referencing:

[1] Di Ma, Fan Zhang and David Bull, “BVI-DVC: A Training Database for Deep Video Compression“, arXiv:2003.13552, 2020.

[2] Di Ma, Fan Zhang and David Bull,”BVI-DVC“, 2020.