Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2026

Abstract

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.

Keywords

Portrait shadow removal, Self-exemplar illumination equalization, Correspondence feature matching, Image processing, Computational photography

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Publication

Proceedings of ACM International Conference on Multimedia (ACM MM 2024) : Melbourne, Australia, October 28 - November 1

First Page

7474

Last Page

7482

Identifier

10.1145/3664647.3681000

Publisher

Association for Computing Machinery

City or Country

Melbourne, Australia

Additional URL

https://doi.org/10.1145/3664647.3681000

Download

Share

COinS