Deep image inpainting

Over the years, many techniques have emerged to reconstruct and modify images for a myriad of applications. One ingenious application is image inpainting, which is to restore the missing parts of an image. The latest approach employs deep learning technique to solve the problem. Deep convolutional n...

Full description

Saved in:
Bibliographic Details
Main Author: Chua, Hao Yang
Other Authors: Chen Change Loy
Format: Final Year Project
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/79001
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-79001
record_format dspace
spelling sg-ntu-dr.10356-790012023-03-03T20:48:34Z Deep image inpainting Chua, Hao Yang Chen Change Loy School of Computer Science and Engineering Engineering::Computer science and engineering Over the years, many techniques have emerged to reconstruct and modify images for a myriad of applications. One ingenious application is image inpainting, which is to restore the missing parts of an image. The latest approach employs deep learning technique to solve the problem. Deep convolutional neural networks are used to capture the abstract details of many training images, so that it can guess the context of a missing region. The performance of the network heavily relies on the information provided upon training. Most work failed to utilize or realize the importance of prior information that may boost the proficiency of neural networks. This project attempts to use segmentation maps as a feature engineering to create supplementary information to aid the image inpainting process. The method of inpainting process proposed will consist of two stages. First is to generate the segmentation maps of the missing region. Second is to take the prior segmentation maps generated for fusion into the inpainting process. Training and evaluation are done on ADE20K dataset with eight categories of segmentation defined and all other bodies as the background category. Bachelor of Engineering (Computer Science) 2019-11-22T12:23:10Z 2019-11-22T12:23:10Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/79001 en Nanyang Technological University 43 p. application/pdf
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
spellingShingle Engineering::Computer science and engineering
Chua, Hao Yang
Deep image inpainting
description Over the years, many techniques have emerged to reconstruct and modify images for a myriad of applications. One ingenious application is image inpainting, which is to restore the missing parts of an image. The latest approach employs deep learning technique to solve the problem. Deep convolutional neural networks are used to capture the abstract details of many training images, so that it can guess the context of a missing region. The performance of the network heavily relies on the information provided upon training. Most work failed to utilize or realize the importance of prior information that may boost the proficiency of neural networks. This project attempts to use segmentation maps as a feature engineering to create supplementary information to aid the image inpainting process. The method of inpainting process proposed will consist of two stages. First is to generate the segmentation maps of the missing region. Second is to take the prior segmentation maps generated for fusion into the inpainting process. Training and evaluation are done on ADE20K dataset with eight categories of segmentation defined and all other bodies as the background category.
author2 Chen Change Loy
author_facet Chen Change Loy
Chua, Hao Yang
format Final Year Project
author Chua, Hao Yang
author_sort Chua, Hao Yang
title Deep image inpainting
title_short Deep image inpainting
title_full Deep image inpainting
title_fullStr Deep image inpainting
title_full_unstemmed Deep image inpainting
title_sort deep image inpainting
publishDate 2019
url http://hdl.handle.net/10356/79001
_version_ 1759854108474343424