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 impossible without modelling a realistic 3D user world. The project aims to provide more realistic VR video experiences by developing a deep-learning model to predict 3D information using the 2D content. For this aim, an adversarial learning based deep learning model will be designed to estimate depth map, providing extended capability for VR video.

Requirement:

Basic understanding of Deep-learning,

Strong Python programming skills with knowledge of Pytorch/tensorflow tools