The SIAM Journal on Imaging Sciences (“SIIMS – a broad authoritative source for fundamental results in imaging sciences, with a unique combination of mathematics and applications”), an influential Q1-journal with a significant Impact Factor and SJR indicator, has just published the paper “Automatically Controlled Morphing of 2D Shapes with Textures” authored by NCCA academics and students. This multidisciplinary paper proposes a novel theoretical and practical framework resulting in a suite of mathematically substantiated techniques important in the context of 2D imagery, artistic design, computer animation, and emerging streaming and interactive applications.
The paper has a rather long and non-trivial history related to the fusion of academic and student research. Initially, NCCA UG student Felix Marrington-Reeve (“Computer Visualisation and Animation” course, Level 6) undertook his R&D project within the “Innovations” unit and got some interesting results. The 8-page paper written on the basis of his project and co-authored with his supervisors Dr Valery Adzhiev and Prof Alexander Pasko, was, however, rejected in 2017 by two international conferences (they were prepared to accept a short version but the authors thought the work deserved a better fate).
After Felix’s graduation (he started working in a leading production company Framestore) Dr Oleg Fryazinov and PhD student Alexander Tereshin joined the project team. A lot of additional theoretical and practical work had been done, and in February 2019 the radically modified and extended 30-page version was submitted to SIIMS. After two-stage rigorous peer-reviewing process, in October 2019 the paper was accepted by this prestigious journal.
- Tereshin, A., Adzhiev, V., Fryazinov, O., Marrington-Reeve, F., Pasko, A. (2020). “Automatically Controlled Morphing of 2D Shapes with Textures”, The SIAM Journal on Imaging Sciences, Vol. 13, No. 1, pp. 78-107. DOI: 10.1137/19M1241581
- Full text of the paper: http://eprints.bournemouth.ac.uk/33366/
“IEEE Computer Graphics and Applications”, an influential magazine with a wide readership in both academia and industry, has just published the paper “4D Cubism: Modeling, Animation and Fabrication of Artistic Shapes”.
This multidisciplinary paper proposing a novel technology on the edge of art and science has been written by a team from the National Centre for Computer Animation (NCCA) of the Faculty of Media and Communication. The authors are Quentin Corker-Marin, Prof Alexander Pasko, and Dr Valery Adzhiev.
The paper has a non-trivial history. Initially, there was an UG student project (“Innovations” unit, “Computer Visualisation and Animation” course, Level 6) that was submitted as a Poster to the ACM SIGGRAPH 2017 conference in Los Angeles. As it was reported in the Research Blog in September 2017, Quentin was awarded there the second prize in the prestigious ACM Student Research Competition sponsored by Microsoft. Then a full-scale paper was submitted to the top magazine, and after successful peer-reviewing it was accepted and published. As to Quentin, in the end of 2017 he graduated from NCCA with a first class honours degree in computer visualisation and animation and works now in London as a 3D Artist for an award-winning production company Glassworks.
Our BU briefing papers are designed to make our research outputs accessible and easily digestible so that our research findings can quickly be applied – whether to society, culture, public policy, services, the environment or to improve quality of life. They have been created to highlight research findings and their potential impact within their field.
In recent years, motion capture data (mocap) have been widely used in computer games, film production and sport sciences. The great success of animated and animation enhanced feature films, such as Avatar, provide compelling evidence for the values of mocap techniques. However, even with the most expensive commercial mocap systems, there are still instances where noise and missing data are inevitable.
This paper examines the motion refinement problem and presents an effective framework to solve it, demonstrated by extensive experiments on both synthetic and real data. The experiment shows that the proposed method outperforms all competitors not only in predicting missing values but also in de-noising most of the time.
Click here to read the briefing paper.
For more information about the research, contact Dr Xiaosong Yang at firstname.lastname@example.org or Professor Jian Jun Zhang at email@example.com.
To find out how your research output could be turned into a BU Briefing, contact firstname.lastname@example.org.