Gaussian Splat-Based Human Performance Reconstruction from Sparse Cameras

Date of Award


Document Type


Degree Name

Master of Science in Computer Vision


Computer Vision

First Advisor

Prof. Fakhri Karray

Second Advisor

Prof. Mohammad Yaqub


Furthermore, a thorough dataset is carefully selected to assess the operation of the virtual human teleportation system in different lighting circumstances, demonstrating the adaptability and reliability of the GPS-Gaussian technique. The graphical interface is designed to be user-friendly and allows for online real-time reconstruction, visualization, and interaction with the virtual human teleportation system. This discovery has consequences that go beyond academic investigation and can be applied in several fields such as remote cooperation, entertainment, healthcare, and education.


Thesis submitted to the Deanship of Graduate and Postdoctoral Studies

In partial fulfilment of the requirements for the M.Sc degree in Computer Vision

Advisors: Hao Li, Salman Khan

Online access available for MBZUAI patrons