Postgrad LIVE! Study Fairs


Nottingham Trent University Featured PhD Programmes
University of West London Featured PhD Programmes
Anglia Ruskin University Featured PhD Programmes
University of Portsmouth Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes

Single Image 3-D Geometry Estimation using Unsupervised Machine Learning (GONGH1U19SF)

Project Description

Most current deep Neural Networks are trained by supervised learning which usually requires massive amounts of manually labelled data (e.g. [i]). Unsupervised learning is a branch of machine learning that learns from unlabelled data without any involvement of human annotators. A toddler has never been taught how to perceive the 3-D world, yet a toddler’s ability of 3-D perception improves over time. It is self-reasoning, and this is what a true intelligence is about for the future Artificial Intelligence (AI) industry.

In this PhD project, we plan to develop an unsupervised machine learning framework to train a deep neural network for 3-D geometry (or depth image) reconstruction from a single image. The ground-breaking novelty of this project is that we do not require a pre-training stage or any labelled ground-truth data (such as the depth images captured by a 3-D scanner). Similar to a toddler’s self-learning, the only training data we use will be the common videos captured by an RGB camera, which can be easily collected from the Internet. We hope to train a machine 3-D geometry perception just by “observing the world”. We plan to achieve this by taking advantage of the between-frame cues such as geometry and illumination consistency [ii-iv]. We also investigate the possibility of using an image-to-image Generative Adversarial Network (GAN) [v]. The developed approach will be evaluated based on some public geometry reconstruction datasets (esp. for data captured from on-car cameras).

The outcome of this project is expected to provide powerful applications in many hot areas of AI such as self-driving cars/drones, mixed-reality engines (for Oculus, Hololens, and Magic Leap), and film visual effects.

A start date prior to October 2019 is possible but should be discussed with Dr Gong in the first instance.

For more information on the supervisor for this project, please go here:
The type of programme: PhD   
The start date of the project: October 2019
The mode of study: full-time
Entry requirements: Acceptable first degree in Computer Science, Mathematics, Physics (or related degree), 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. The amount charged annually will vary considerably depending on the nature of the project and applicants should contact the primary supervisor for further information about the fee associated with the project.


i) Eigen, David, Christian Puhrsch, and Rob Fergus. "Depth map prediction from a single image using a multi-scale deep network." Advances in neural information processing systems. 2014.
ii) Garg, Ravi, et al. "Unsupervised cnn for single view depth estimation: Geometry to the rescue." ECCV. Springer, Cham, 2016.
iii) Godard, Clément, Oisin Mac Aodha, and Gabriel J. Brostow. "Unsupervised monocular depth estimation with left-right consistency." CVPR. Vol. 2. No. 6. 2017.
iv) Finlayson, Graham, Gong, Han, and Fisher, Robert. "Color Homography: theory and applications." IEEE Transactions on Pattern Analysis and Machine Intelligence (2017).
v) Liu, Ming-Yu, Thomas Breuel, and Jan Kautz. "Unsupervised image-to-image translation networks." Advances in Neural Information Processing Systems. 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.