Please use this identifier to cite or link to this item:
Title: RainGAN: unsupervised raindrop removal via decomposition and composition
Authors: Xu, Yan
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Xu, Y. (2022). RainGAN: unsupervised raindrop removal via decomposition and composition. Master's thesis, Nanyang Technological University, Singapore.
Abstract: Adherent raindrops on windshield or camera lens may distort and occlude vision, causing issues for downstream machine vision perception. Most of the existing raindrop removal methods focus on learning the mapping from a raindrop image to its clean content by training with the paired raindrop-clean images. However, the paired real-world images are difficult to collect in practice. This thesis presents a novel framework for raindrop removal that eliminates the need for paired training samples. Based on the assumption that a raindrop image is the composition of a clean image and a raindrop style, the proposed framework decomposes a raindrop image into a clean content image and a raindrop-style latent code and composes a clean content image and a raindrop style code to a raindrop image for data augmentation. The proposed framework introduces a domain-invariant residual block to facilitate the identity mapping for the clean portion of the raindrop image. Extensive experiments on real-world raindrop datasets show that our network can achieve superior performance in raindrop removal to other unpaired image-to-image translation methods, even with comparable performance with state-of-the-art methods that require paired images.
DOI: 10.32657/10356/160029
Schools: School of Computer Science and Engineering 
Organisations: NCS Pte Ltd
Rights: This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Theses

Files in This Item:
File Description SizeFormat 
Xu_Yan_Thesis.pdf34.6 MBAdobe PDFThumbnail

Page view(s)

Updated on Jun 6, 2023

Download(s) 50

Updated on Jun 6, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.