Real-time Dense 3D Reconstruction with RGB-D Camera

MPhil Thesis Defence


Title: "Real-time Dense 3D Reconstruction with RGB-D Camera"

By

Mr. Hanyu DENG


Abstract

Real-time surface mapping and tracking is the core technology behind 
augmented reality applications. The growing trend of integrating depth 
sensors into mobile devices provides a great opportunity for enhancing the 
experience of interaction with reality. This work present a system that 
utilizes the RGB-D cameras of mobile device, for tracking and 
reconstructing dense surface in real-time. This task is challenging 
because the low computing power and memory capacity on consumer mobile 
platform limits the scale and precision of the reconstruction. To scale up 
scene size and provide smooth integration experience, we implemented 
memory efficient data representation and caching methods, and also make 
the integration and visualization processes highly parallel. This thesis 
illustrates the implementation of each pipeline stage, including the 
underlying data structure, pre-processing, tracking, integration, 
rendering and caching. The overall performance evaluation and its 
application are also demonstrated with conclusion.


Date:			Thursday, 14 November 2019

Time:			2:00pm - 4:00pm

Venue:			Room CYTG001
 			Lifts 35/36

Committee Members:	Prof. Long Quan (Supervisor)
 			Dr. Pedro Sander (Chairperson)
 			Prof. Chiew-Lan Tai


**** ALL are Welcome ****