Coventry University Featured PhD Programmes
University of Southampton Featured PhD Programmes
University College London Featured PhD Programmes
Heriot-Watt University Featured PhD Programmes
University of Reading Featured PhD Programmes

Deep learning for image colour transfer (GONGH2U20SF)

Project Description

Colours may vary from image to image. This may be caused by different capture conditions (e.g. illumination, camera), seasons, object reflectances, and post-processing. Colour transfer is a process that transfers one image’s colour palette to another image. The leading solutions often require a large number of modelling parameters, high computational cost, or expensive image registration. Without the loss of accuracy, it is often desirable to avoid complex image registrations and artefacts while unifying the colours among different captures.

In this PhD project, we aim to develop new algorithms for transferring colours between two images or among a set of video frames. These algorithms provide powerful applications, in particular, the art and film industry (e.g. “Match Color” in Apple FinalCut) whereby colour transfer is often required for blending one video sequence with another. In mobile-end video editing apps, a video colour stabilization [i-ii] is also desirable for providing a smooth and consistent colour transition between video frames. The project will begin by inspecting classic colour transfer methods based on image intensity statistics [i-ii]. We then combine the classic approaches with the neural networks [iii] to achieve a real-time and high-quality performance. Depending on the application scenario, we plan to develop two different solutions of colour transfer for the same scene (useful for video colour stabilisation) and the unknown different scenes (useful for creative graphics editing).

The outcome of this project is expected to provide powerful applications in video editing and digital creative art productions.

A start date prior to October 2020 is possible but this should be discussed with Dr Gong in the first instance.

For more information on the supervisor for this project, please go here:

This is a PhD programme.

The start date of the project is 1 October 2020.

The mode of study is full-time. The studentship length is 3 years with a 1-year registration period.

Please note: Applications are processed as soon as they are received and the project may be filled before the closing date, so early application is encouraged.

Entry requirements:

Acceptable first degree in Computer Science, Mathematics, Physics, Engineering (or other related STEM subjects).

The standard minimum entry requirement is 2:1.

Funding Notes

This PhD project is offered on a self-funding basis. It is open to applicants with funding or those applying to funding sources. Details of tuition fees can be found at View Website.

A bench fee is also payable on top of the tuition fee to cover specialist equipment or laboratory costs required for the research. Applicants should contact the primary supervisor for further information about the fee associated with the project.


) Farbman, Zeev, and Dani Lischinski. "Tonal stabilization of video." ACM Transactions on Graphics (TOG). Vol. 30. No. 4. ACM, 2011.

ii) Gong, Han, et al. "3D color homography model for photo-realistic color transfer re-coding." The Visual Computer (2017): 1-11.

iii) Luan, Fujun, et al. "Deep Photo Style Transfer." 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.