Portrait shadow removal via self-exemplar illumination equalization
We introduce the Self-Exemplar Illumination Equalization Network, designed specifically for effective portrait shadow removal. The core idea of our method is that partially shadowed portraits can find ideal exemplars within their non-shadowed facial regions. Rather than directly fusing two distinct...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2026
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9767 https://ink.library.smu.edu.sg/context/sis_research/article/10767/viewcontent/3664647.3681000__1_.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-10767 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-107672024-12-16T02:40:01Z Portrait shadow removal via self-exemplar illumination equalization HUANG, Qian XU, Cheng LI, Guiqing WU, Ziheng LIU, Shengxin HE, Shengfeng We introduce the Self-Exemplar Illumination Equalization Network, designed specifically for effective portrait shadow removal. The core idea of our method is that partially shadowed portraits can find ideal exemplars within their non-shadowed facial regions. Rather than directly fusing two distinct classes of facial features, our approach utilizes non-shadowed regions as an illumination indicator to equalize the shadowed regions, generating deshadowed results without boundary-merging artifacts. Our network comprises cascaded Self-Exemplar Illumination Equalization Blocks (SExmBlock), each containing two modules: a self-exemplar feature matching module and a feature-level illumination rectification module. The former identifies and applies internal illumination exemplars to shadowed areas, producing illumination-corrected features, while the latter adjusts shadow illumination by reapplying the illumination factors from these features to the input face. Applying this series of SExmBlocks to shadowed portraits incrementally eliminates shadows and preserves clear, accurate facial details. The effectiveness of our method is demonstrated through evaluations on two public shadow portrait datasets, where it surpasses existing state-of-the-art methods in both qualitative and quantitative assessments. 2026-04-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9767 info:doi/10.1145/3664647.3681000 https://ink.library.smu.edu.sg/context/sis_research/article/10767/viewcontent/3664647.3681000__1_.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 Portrait shadow removal Self-exemplar illumination equalization Correspondence feature matching Image processing Computational photography Artificial Intelligence and Robotics 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 |
Portrait shadow removal Self-exemplar illumination equalization Correspondence feature matching Image processing Computational photography Artificial Intelligence and Robotics Graphics and Human Computer Interfaces |
spellingShingle |
Portrait shadow removal Self-exemplar illumination equalization Correspondence feature matching Image processing Computational photography Artificial Intelligence and Robotics Graphics and Human Computer Interfaces HUANG, Qian XU, Cheng LI, Guiqing WU, Ziheng LIU, Shengxin HE, Shengfeng Portrait shadow removal via self-exemplar illumination equalization |
description |
We introduce the Self-Exemplar Illumination Equalization Network, designed specifically for effective portrait shadow removal. The core idea of our method is that partially shadowed portraits can find ideal exemplars within their non-shadowed facial regions. Rather than directly fusing two distinct classes of facial features, our approach utilizes non-shadowed regions as an illumination indicator to equalize the shadowed regions, generating deshadowed results without boundary-merging artifacts. Our network comprises cascaded Self-Exemplar Illumination Equalization Blocks (SExmBlock), each containing two modules: a self-exemplar feature matching module and a feature-level illumination rectification module. The former identifies and applies internal illumination exemplars to shadowed areas, producing illumination-corrected features, while the latter adjusts shadow illumination by reapplying the illumination factors from these features to the input face. Applying this series of SExmBlocks to shadowed portraits incrementally eliminates shadows and preserves clear, accurate facial details. The effectiveness of our method is demonstrated through evaluations on two public shadow portrait datasets, where it surpasses existing state-of-the-art methods in both qualitative and quantitative assessments. |
format |
text |
author |
HUANG, Qian XU, Cheng LI, Guiqing WU, Ziheng LIU, Shengxin HE, Shengfeng |
author_facet |
HUANG, Qian XU, Cheng LI, Guiqing WU, Ziheng LIU, Shengxin HE, Shengfeng |
author_sort |
HUANG, Qian |
title |
Portrait shadow removal via self-exemplar illumination equalization |
title_short |
Portrait shadow removal via self-exemplar illumination equalization |
title_full |
Portrait shadow removal via self-exemplar illumination equalization |
title_fullStr |
Portrait shadow removal via self-exemplar illumination equalization |
title_full_unstemmed |
Portrait shadow removal via self-exemplar illumination equalization |
title_sort |
portrait shadow removal via self-exemplar illumination equalization |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2026 |
url |
https://ink.library.smu.edu.sg/sis_research/9767 https://ink.library.smu.edu.sg/context/sis_research/article/10767/viewcontent/3664647.3681000__1_.pdf |
_version_ |
1819113132853821440 |