Thesis and Final Year Project Proposals

15th September 2017
Thesis and Final Year Project Proposals

Instructions to students:
  1. If you are interested in any topic or have any inquiries relating to the topic, please contact the proposer(s) who created the topic via their email listed below each name for each topic heading, and please copy the Administrator Gail Weadick gail.weadick at scss.tcd.ie.
  2. Once you have agreed on the topic with the proposer(s) and made your decision, please register your topic with Professor Smolic by emailing smolica at scss.tcd.ie and please copy the Administrator Gail Weadick gail.weadick at scss.tcd.ie.

Available

Deep-learning based music localization in VR using audio-visual cues
Proposed by Aakanksha Rana and Cagri Ozcinar Email: ranaa at scss.tcd.ie or ozcinarc at scss.tcd.ie Are you interested in developing solutions ...
Read More
Generating realistic VR using deep-learning
Proposed by Aakanksha Rana and Cagri Ozcinar Email: ranaa at scss.tcd.ie or ozcinarc at scss.tcd.ie A true sense of VR is ...
Read More
Audio-visual attention modeling using deep-learning for VR
Proposed by Aakanksha Rana and Cagri Ozcinar Email: ranaa at scss.tcd.ie or ozcinarc at scss.tcd.ie With recent interest in increased immersion, ...
Read More
A New Method for Compression of Free Viewpoint Videos
Proposed by Iman Zolanvari Email: Iman dot zolanvari at scss.tcd.ie Free Viewpoint Videos (FVV) are relatively new technology and a ...
Read More
Evaluating the Aesthetic Quality of Light Field Images Using Deep Learning
Proposed by Koustav Ghosal, Sebastian Lutz
Email: {ghosalk / lutzs} at scss.tcd.ie
In this project, the primary task will be ...
Read More
Understanding the Geometry of Photographic Images Using Deep Learning
Proposed by Koustav Ghosal, Sebastian Lutz
Email: {ghosalk / lutzs} at scss.tcd.ie
The goal of this project is to explore ...
Read More
Adversarial Multi-task Learning for Aesthetic Analysis and Enhancement of Photographic Images
Proposed by Koustav Ghosal, Sebastian Lutz, Tejo Chalasani
Email: {ghosalk / lutzs / chalasat} at scss.tcd.ie
The aim of this ...
Read More
Parallelization of low rank matrix completion algorithms
Proposed by Mikael Le Pendu
Email: lependum at scss.tcd.ie
The problem of recovering a matrix from a subset of its ...
Read More
Deep Spherical Harmonics
Proposed by Matis Hudon
Email: hudonm at scss.tcd.ie
Figure 1: Spherical Harmonics Representation Figure 2: Convolutional Neural Network Example In ...
Read More
Creation of light field panoramas with a Lytro Illum camera and Syrp Genie Mini
Proposed by: Martin Alain - alainm at scss.tcd.ie
Mikael Le Pendu - lependum at scss.tcd.ie
The goal of this ...
Read More
Creation of a synthetic light field dataset for deep learning applications
Proposed by: Martin Alain - alainm at scss.tcd.ie
David Hardman - hardmand at scss.tcd.ie
Yang Chen - cheny5 at scss.tcd.ie
...
Read More
Deep style transfer for light fields
Proposed by: Martin Alain - alainm at scss.tcd.ie
Mairead Grogan - groganma at scss.tcd.ie
Yang Chen - cheny5 at scss.tcd.ie
...
Read More
Comparison of a point cloud compression methods and benchmark of objective quality metrics
Proposed by Emin Zerman - zermane at scss.tcd.ie
Point clouds (PC) are a popular representation method both for static 3D models ...
Read More
User behaviour analysis and modelling for augmented reality and virtual reality multimedia
Proposed by Emin Zerman - zermane at scss.tcd.ie
Capturing and displaying volumetric videos are becoming easier with the developing technology for ...
Read More
Deep learning based Generative Inpainting for VR
Proposed by Aakanksha Rana and Cagri Ozcinar Email: ranaa at scss.tcd.ie or ozcinarc at scss.tcd.ie Due to its interactive look-around consumption ...
Read More
Neural style transfer for videos
Proposed by Pierre Matysiak and Mairéad Grogan
Email : matysiap at scss.tcd.ie or mgrogan at tcd.ie
Style ...
Read More

Ongoing

Bringing Life to the Book of Kells Busts
Proposed by Iman Zolanvari Email: Iman dot zolanvari at scss.tcd.ie Book of Kells library has busts of many great philosophers ...
Read More
An AR Door to the History of TCD
Proposed by Iman Zolanvari & Rogerio da Silva
Email: Iman dot zolanvari at scss.tcd.ie or rogerio dot silva at tcd dot ...
Read More
Developing AR navigation app for TCD
Proposed by Iman Zolanvari Email: Iman dot zolanvari at scss.tcd.ie Trinity College Dublin (TCD) is one of the most tourist ...
Read More
Interactive Gaming Gesture on AR Environment
Proposed by Iman Zolanvari Email: Iman dot zolanvari at scss.tcd.ie Realistic AR games have become recently a popular research topic ...
Read More
Bitrate adaptive quantisation for omnidirectional video with a 3DoF+ capability
Proposed by Cagri Ozcinar Email: ozcinarc at scss.tcd.ie<br/ > Due to its large amount of bandwidth requirement, delivery of ...
Read More

Completed

Video compression and streaming for virtual reality and augmented reality
Proposed by Cagri Ozcinar Email: ozcinarc at scss.tcd.ie ...
Read More
Asymmetric compression for stereo omnidirectional VR video
Proposed by Cagri Ozcinar and Simone Croci Email: ozcinarc at scss.tcd.ie or crocis at scss.tcd.ie Considering its data-intensive representation ...
Read More
Real-time 3D skeleton reconstruction using multi-view sequences
Proposed by Rafael Pagés
This project will investigate the possibilities of real time 3D skeleton estimation using multi-view video sequences ...
Read More
3D point cloud motion tracking
Proposed by Rafael Pagés
Image-based 3D reconstruction is a very well studied field, however, there is still a lot of ...
Read More
Multi-view video synchronisation in the wild
Proposed by Rafael Pagés
This project will study the possibilities of multi-view video synchronisation. These kind of sequences are sometimes ...
Read More
Palette Based Image Recolouring using Neural Networks
Proposed by Mairéad Grogan
Email: mgrogan at tcd.ie
Image recolouring is an important application in computer vision, and can be used ...
Read More
Extending soft segmentation for images to video sequences
Proposed by Mairéad Grogan
Email: mgrogan at tcd.ie
Decomposing an image into layers is an important tool when applying further processing ...
Read More
Camera Localisation using Deep Learning for Free View-point Video Applications 
Proposed by Konstantinos Amplianitis
Summary: Free view-point video (FVV) is a system for viewing an event or a performance, allowing ...
Read More
Data augmentation with artistic style
Proposed by: Sebastian Lutz, Tejo Chalasani, Koustav Ghosal
Input Image and 3 different styles. For humans it is still easy ...
Read More
Extending improvements in visual saliency estimation to omnidirectional images
Proposed by: Sebastian Lutz, Tejo Chalasani, Koustav Ghosal
The goal of visual saliency estimation is to predict which parts of an ...
Read More
AR Campus Tour
Proposed by: Sebastian Lutz, Tejo Chalasani, Koustav Ghosal
The idea of this project is to build an AR campus tour guide ...
Read More
Automatic Irish Sign Language Recognition
Proposed by: Sebastian Lutz, Tejo Chalasani, Koustav Ghosal
CNN for gesture recognition has been applied for American Sign Language extensively ...
Read More