Rain removal using cycle-consistency adversarial network

Raindrops in videos and images can hamper the visibility of objects in a scene, leading to a loss of video quality. In this project, we address the problem of rain removal in images by using an unsupervised learning approach relying on a new framework of cycle-consistent generative adversarial netwo...

Full description

Saved in:
Bibliographic Details
Main Author: Ng, Henry Siong Hock
Other Authors: Lu Shijian
Format: Final Year Project
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/76949
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-76949
record_format dspace
spelling sg-ntu-dr.10356-769492023-03-03T20:27:45Z Rain removal using cycle-consistency adversarial network Ng, Henry Siong Hock Lu Shijian School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering Raindrops in videos and images can hamper the visibility of objects in a scene, leading to a loss of video quality. In this project, we address the problem of rain removal in images by using an unsupervised learning approach relying on a new framework of cycle-consistent generative adversarial networks. Unlike usual image domain transfer problem, the proposed solution solves the problem by having two asymmetric functions: a forward function that removes the rain from a rain degraded image and a backward function that adds rain into a rain-free clean image. The main idea is to have two coupled generative adversarial network that implements these two functions: one that would remove rain from a rain degraded image and a second network that would add rain into a rain-free clean image. Our experiments show the effectiveness of our approach and how it performs against other previous works. Bachelor of Engineering (Computer Science) 2019-04-25T07:05:52Z 2019-04-25T07:05:52Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/76949 en Nanyang Technological University 49 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 DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Ng, Henry Siong Hock
Rain removal using cycle-consistency adversarial network
description Raindrops in videos and images can hamper the visibility of objects in a scene, leading to a loss of video quality. In this project, we address the problem of rain removal in images by using an unsupervised learning approach relying on a new framework of cycle-consistent generative adversarial networks. Unlike usual image domain transfer problem, the proposed solution solves the problem by having two asymmetric functions: a forward function that removes the rain from a rain degraded image and a backward function that adds rain into a rain-free clean image. The main idea is to have two coupled generative adversarial network that implements these two functions: one that would remove rain from a rain degraded image and a second network that would add rain into a rain-free clean image. Our experiments show the effectiveness of our approach and how it performs against other previous works.
author2 Lu Shijian
author_facet Lu Shijian
Ng, Henry Siong Hock
format Final Year Project
author Ng, Henry Siong Hock
author_sort Ng, Henry Siong Hock
title Rain removal using cycle-consistency adversarial network
title_short Rain removal using cycle-consistency adversarial network
title_full Rain removal using cycle-consistency adversarial network
title_fullStr Rain removal using cycle-consistency adversarial network
title_full_unstemmed Rain removal using cycle-consistency adversarial network
title_sort rain removal using cycle-consistency adversarial network
publishDate 2019
url http://hdl.handle.net/10356/76949
_version_ 1759853354463264768