Please use this identifier to cite or link to this item:
Title: Single image reflection removal with camera calibration
Authors: Chen, Jinnan
Keywords: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Engineering::Electrical and electronic engineering
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Chen, J. (2021). Single image reflection removal with camera calibration. Master's thesis, Nanyang Technological University, Singapore.
Abstract: With the rapid development of deep learning algorithms and powerful computing hardware, some classic ill-posed computer vision problems could be better solved in a data-driven manner. For single image reflection removal, researchers use different prior knowledge to make the loss design more reasonable. My research on this topic is based on the prior knowledge of physical modeling of the reflection formation. I integrated my research work in NTU as a master by research student into this final thesis, with the title of Stationary Single Image Reflection Removal: Physical Rule to Robustness. This thesis mainly aims to analyze and give a reliable answer to ‘how to encode the physical information into the designed network thus making it easily generalized in the real world and robust to some input perturbations’, before which, some new ideas and in-depth investigation about the robustness of CNN-based model in terms of adversarial perturbations are introduced. The main part of the thesis consists of two specific physical-rule-based models to simulate the reflection formation process. The first one focuses on how to use the pixel-wise reflection coefficient map to guide the reflection removal process as well as calibrate the camera parameters while the second one focuses on how to add constraints to stabilize the output in terms of the perturbations from some physical parameters of the glass which have a great effect to the reflection part. Substantial experimental results and analysis show the effectiveness and the superiority of the proposed methods in the different real scenarios and this research could have a broad impact on other computer vision problems.
DOI: 10.32657/10356/150528
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:EEE Theses

Files in This Item:
File Description SizeFormat Thesis of Jinnan Chen.pdf27.46 MBAdobe PDFView/Open

Page view(s)

Updated on Jan 21, 2022

Download(s) 50

Updated on Jan 21, 2022

Google ScholarTM




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