UROP Project Listing System
 
Project Title:
3D Scene Generation with Scanned RGB-D data
Supervisor:YEUNG Sai Kit
Co-Supervisor:-
Quota:5
Project Description:Indoor scene understanding requires a large amount of 3D data. However, building such data takes a lot of efforts. In this project, we use scanned RGB-D data to learn a generative model for these 3D scenes. The generative model can later be used for data generation, scene understanding and human-assited design process.
Course type: UROP1100  
Applicant's Roles:Required Skill: basic C++/Python programming, computer graphics background is preferred 
Applicant's Learning Objectives:The students will learn about deep learning techniques for scene generation and understanding. They will get training on data processing and how to build a 3D application. 
Complexity of the project:Moderate 
 



Copyright © 2016 HKUST. All rights reserved.