Rafał Mantiuk *
Rafał Mantiuk
Reader in Graphics and Displays
Department of Computer Science and Technology
The Computer Laboratory
Rainbow Research Group
University of Cambridge

Office address
University of Cambridge
Computer Laboratory
William Gates Building
15 JJ Thomson Avenue
Cambridge CB3 0FD
United Kingdom
office: +44 1223 763831
rafal [dot] mantiuk [at] cl [dot] cam [dot] ac [dot] uk

Important: if you have never sent or received e-mail from me, please include the text "n0t5pam" somewhere in the subject line, for example "[n0t5pam] Your subject". This is to avoid the SPAM filter.

If you are contacting me about internship, PhD studentship, or a PostDoc position, please check the "Jobs" section first.

Reserach interest

Applied visual perception; high dynamic range imaging; display algorithms; tone-mapping; video coding for new display technologies; image and video quality metric; visibility metrics; virtual reality and low-level perception; computational photography; computational displays; novel display technologies; colour; perception in computer graphics; novel image and video representations (beyond 2D); psychophysics; modeling visual perception with machine learning.


Senior Lecturer, University of Cambridge, Computer Laboratory, UK (from 2015)
Lecturer / Senior Lecturer, Bangor University, School of Computer Science, UK (2009-2015)
Postdoc Fellow, University of British Columbia, Canada (2008-2009)
Postdoc, Max-Planck-Institut for Computer Science, Germany (2007-2008)
Internship, Sharp Laboratories of America, Camas WA, USA (2006)
PhD (summa cum laude, Computer Science), Max-Planck-Institut for Computer Science, Germany (2006)
Msc (Computer Science), Technical University of Szczecin, Poland (2003)
Google Scholar LinkedIn profile Mendeley profile

Recent projects

Project image
Single-frame Regularization for Temporally Stable CNNs

We make generative CNNs produce temporarily coherent video by adding regularization terms to the loss function. The regularization facilitates learning geometric transformations, which should affect the output frame in the same way as the input frame.

Project image
Temporal Resolution Multiplexing: Exploiting the limitations of spatio-temporal vision for more efficient VR rendering

Every second frame of a high-frame animation is rendered at a lower resolution, reducing the number of rendered and transmitted pixels by about 40%. The high quality animation is reconstructed by exploiting the limitations of human spatio-temporal vision.

Project image
Dataset and metrics for predicting local visible differences

Visibility of artifacts is marked by a number of observers to create a dataset of local differences. The dataset is then used to retrain existing visibility metrics, such as HDR-VDP-2, and to train a new CNN-based metric.

See more projects.

Recent papers

See all papers.

Awards and grants

My contribution to the organization of research networks and conferences can be found here.