3D human modelling
In recent years, applications such as virtual reality or augmented reality have been gaining popularity as technology progresses rapidly. In particular, the use of 3D objects within these applications has encouraged the acquisition of 3D models to become easier and more accessible to the general pub...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/147910 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-147910 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1479102021-04-16T06:09:23Z 3D human modelling Tan, Jia Le Chen Change Loy School of Computer Science and Engineering ccloy@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision In recent years, applications such as virtual reality or augmented reality have been gaining popularity as technology progresses rapidly. In particular, the use of 3D objects within these applications has encouraged the acquisition of 3D models to become easier and more accessible to the general public. In view of this, the developer community explored the possibility of modelling a 3D human model from a single image using deep neural networks. While geometry reconstruction of 3D human model has achieved substantial progress, texture reconstruction has received little attention from the community in this regard. In this study, we identify the limitations in the current texture reconstruction framework: (i) texture around unseen regions are featureless (ii) single image reconstruction does not provide sufficient texture information. To address this, we propose Simulated Multi-View Texture Inference Network, an architecture simulating a multi-view texture inference, which circumvents the need for an implicit function to hallucinate the texture around unseen regions. We show that our approach can produce human mesh with consistent texture and perform better than other approaches in some cases. We also conducted experiments to evaluate our approach quantitatively and qualitatively in our study. Bachelor of Engineering (Computer Engineering) 2021-04-16T06:09:23Z 2021-04-16T06:09:23Z 2021 Final Year Project (FYP) Tan, J. L. (2021). 3D human modelling. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/147910 https://hdl.handle.net/10356/147910 en SCSE20-0409 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
spellingShingle |
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Tan, Jia Le 3D human modelling |
description |
In recent years, applications such as virtual reality or augmented reality have been gaining popularity as technology progresses rapidly. In particular, the use of 3D objects within these applications has encouraged the acquisition of 3D models to become easier and more accessible to the general public. In view of this, the developer community explored the possibility of modelling a 3D human model from a single image using deep neural networks. While geometry reconstruction of 3D human model has achieved substantial progress, texture reconstruction has received little attention from the community in this regard. In this study, we identify the limitations in the current texture reconstruction framework: (i) texture around unseen regions are featureless (ii) single image reconstruction does not provide sufficient texture information. To address this, we propose Simulated Multi-View Texture Inference Network, an architecture simulating a multi-view texture inference, which circumvents the need for an implicit function to hallucinate the texture around unseen regions. We show that our approach can produce human mesh with consistent texture and perform better than other approaches in some cases. We also conducted experiments to evaluate our approach quantitatively and qualitatively in our study. |
author2 |
Chen Change Loy |
author_facet |
Chen Change Loy Tan, Jia Le |
format |
Final Year Project |
author |
Tan, Jia Le |
author_sort |
Tan, Jia Le |
title |
3D human modelling |
title_short |
3D human modelling |
title_full |
3D human modelling |
title_fullStr |
3D human modelling |
title_full_unstemmed |
3D human modelling |
title_sort |
3d human modelling |
publisher |
Nanyang Technological University |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/147910 |
_version_ |
1698713669592940544 |