University of Edinburgh Featured PhD Programmes
University of Southampton Featured PhD Programmes
University of Glasgow Featured PhD Programmes

Deep learning for low-light photographing (GONGHU20SF)


School of Computing Sciences

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
Dr H Gong , Prof G Finlayson No more applications being accepted

About the Project

Have you ever struggled in taking a good photo in low light? Despite the dramatic improvements in camera sensors, photographing in darkness is still challenging because in many conditions, there is simply too little light on the scene and the camera sensors are sensitive to noise in these conditions. This may be compensated by increasing exposure time. However, a problem is that this can also introduce motion blur thus we need to reduce video capturing frame rate to minimise the number of blurs for this some image “de-noising”, “de-blurring” and enhancement methods (e.g. [ii-iii]) have been proposed, but their applicability is limited in dim light conditions. In general, they are not suitable for real-time video capture in the extremely low light condition.

In this PhD project, we plan to develop a pipeline for enhancing nearly black images/videos taken in low light using Deep Learning and Artificial Intelligence (AI). We will start by developing a supervised learning approach which does require some ground truth pairs of dark images and well-lit images for training. In the next stage, we will further investigate an unsupervised learning framework which does not require any corresponding ground truth image pairs. Instead, the training will be based on analysing different un-annotated sets of dark and well-lit images. We will also compare our solution with start-of-the-art methods (e.g. [I,ii]) using both quantitative evaluation and user experiments.

The outcome of this project is expected to provide powerful applications in smartphone camera development and night-time surveillance.

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


MORE INFORMATION

Project supervisor: https://people.uea.ac.uk/h_gong
Mode of study: Full time
Start date: October 2020
Entry requirements: First degree (2:1 or above) in Computer Science, Mathematics, Physics, Engineering (or other related STEM subjects).

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 http://www.uea.ac.uk/study/postgraduate/research-degrees/fees-and-funding.

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.

References

Chen, Chen, et al. "Learning to See in the Dark." CVPR 2018.

Guo, Xiaojie, Yu Li, and Haibin Ling. "LIME: Low-light image enhancement via illumination map estimation." IEEE Transactions on Image Processing 26.2 (2017): 982-993.

Hu, Zhe, et al. "Deblurring Low-light Images with Light Streaks." IEEE Transactions on Pattern Analysis and Machine Intelligence (2017).
Search Suggestions

Search Suggestions

Based on your current searches we recommend the following search filters.



FindAPhD. Copyright 2005-2021
All rights reserved.