Be an environment artist: generating scene lightings using generative adversarial network

Be an environment artist: generating scene lightings using generative adversarial network

This project aimed to develop a framework of text-driven 360-degree panoramic image generation and image stylization. With the use of Generative Adversarial Networks, Text2Light was used as the preliminary model for panorama generation. The text-driven image stylization was done using Stable Diffusi...

Full description

Saved in:
Bibliographic Details
Main Author: Wang, Xuege
Other Authors: Liu Ziwei
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Online Access:https://hdl.handle.net/10356/166162
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-166162
record_format dspace
spelling sg-ntu-dr.10356-1661622023-04-21T15:39:28Z Be an environment artist: generating scene lightings using generative adversarial network Wang, Xuege Liu Ziwei School of Computer Science and Engineering ziwei.liu@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision This project aimed to develop a framework of text-driven 360-degree panoramic image generation and image stylization. With the use of Generative Adversarial Networks, Text2Light was used as the preliminary model for panorama generation. The text-driven image stylization was done using Stable Diffusion models. A detailed set of experiments were done to explore the best model among the proposed 4 pipelines. A ThreeJS based demonstration page was developed as a proof-of-concept. Bachelor of Engineering (Computer Science) 2023-04-19T01:39:56Z 2023-04-19T01:39:56Z 2023 Final Year Project (FYP) Wang, X. (2023). Be an environment artist: generating scene lightings using generative adversarial network. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166162 https://hdl.handle.net/10356/166162 en SCSE22-0192 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
Wang, Xuege
Be an environment artist: generating scene lightings using generative adversarial network
description This project aimed to develop a framework of text-driven 360-degree panoramic image generation and image stylization. With the use of Generative Adversarial Networks, Text2Light was used as the preliminary model for panorama generation. The text-driven image stylization was done using Stable Diffusion models. A detailed set of experiments were done to explore the best model among the proposed 4 pipelines. A ThreeJS based demonstration page was developed as a proof-of-concept.
author2 Liu Ziwei
author_facet Liu Ziwei
Wang, Xuege
format Final Year Project
author Wang, Xuege
author_sort Wang, Xuege
title Be an environment artist: generating scene lightings using generative adversarial network
title_short Be an environment artist: generating scene lightings using generative adversarial network
title_full Be an environment artist: generating scene lightings using generative adversarial network
title_fullStr Be an environment artist: generating scene lightings using generative adversarial network
title_full_unstemmed Be an environment artist: generating scene lightings using generative adversarial network
title_sort be an environment artist: generating scene lightings using generative adversarial network
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/166162
_version_ 1764208057249693696

Similar Items