Sparsity based reflection removal using external patch search
Reflection removal aims at separating the mixture of the desired background scenes and the undesired reflections, when the photos are taken through the glass. It has both aesthetic and practical applications which can largely improve the performance of many multimedia tasks. Existing reflection remo...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2017
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/5480 https://ink.library.smu.edu.sg/context/sis_research/article/6483/viewcontent/Sparsity_based_reflection_removal_using_external_patch_search.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-6483 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-64832020-12-24T02:48:10Z Sparsity based reflection removal using external patch search WAN, Renjie SHI, Boxin TAN, Ah-hwee KOT, Alex C. Reflection removal aims at separating the mixture of the desired background scenes and the undesired reflections, when the photos are taken through the glass. It has both aesthetic and practical applications which can largely improve the performance of many multimedia tasks. Existing reflection removal approaches heavily rely on scene priors such as separable sparse gradients brought by different levels of blur, and they easily fail when such priors are not observed in many real scenes. Sparse representation models and nonlocal image priors have shown their effectiveness in image restoration with self similarity. In this work, we propose a reflection removal method benefited from the sparsity and nonlocal image prior as a unified optimization framework. We leverage the retrieved image patch from an external database to overcome the limited prior information in the input mixture image and self similarity search. The experimental results show that our proposed model performs better than the existing stateof-the-art reflection removal method for both objective and subjective image qualities. 2017-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5480 info:doi/10.1109/ICME.2017.8019527 https://ink.library.smu.edu.sg/context/sis_research/article/6483/viewcontent/Sparsity_based_reflection_removal_using_external_patch_search.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Reflection removal image retrieval external dataset sparse representation Databases and Information Systems Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Reflection removal image retrieval external dataset sparse representation Databases and Information Systems Graphics and Human Computer Interfaces |
spellingShingle |
Reflection removal image retrieval external dataset sparse representation Databases and Information Systems Graphics and Human Computer Interfaces WAN, Renjie SHI, Boxin TAN, Ah-hwee KOT, Alex C. Sparsity based reflection removal using external patch search |
description |
Reflection removal aims at separating the mixture of the desired background scenes and the undesired reflections, when the photos are taken through the glass. It has both aesthetic and practical applications which can largely improve the performance of many multimedia tasks. Existing reflection removal approaches heavily rely on scene priors such as separable sparse gradients brought by different levels of blur, and they easily fail when such priors are not observed in many real scenes. Sparse representation models and nonlocal image priors have shown their effectiveness in image restoration with self similarity. In this work, we propose a reflection removal method benefited from the sparsity and nonlocal image prior as a unified optimization framework. We leverage the retrieved image patch from an external database to overcome the limited prior information in the input mixture image and self similarity search. The experimental results show that our proposed model performs better than the existing stateof-the-art reflection removal method for both objective and subjective image qualities. |
format |
text |
author |
WAN, Renjie SHI, Boxin TAN, Ah-hwee KOT, Alex C. |
author_facet |
WAN, Renjie SHI, Boxin TAN, Ah-hwee KOT, Alex C. |
author_sort |
WAN, Renjie |
title |
Sparsity based reflection removal using external patch search |
title_short |
Sparsity based reflection removal using external patch search |
title_full |
Sparsity based reflection removal using external patch search |
title_fullStr |
Sparsity based reflection removal using external patch search |
title_full_unstemmed |
Sparsity based reflection removal using external patch search |
title_sort |
sparsity based reflection removal using external patch search |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2017 |
url |
https://ink.library.smu.edu.sg/sis_research/5480 https://ink.library.smu.edu.sg/context/sis_research/article/6483/viewcontent/Sparsity_based_reflection_removal_using_external_patch_search.pdf |
_version_ |
1770575474133565440 |