A lightweight deep exclusion unfolding network for Single Image Reflection Removal
File(s)
Accepted version
Author(s)
Type
Journal Article
Abstract
Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8% of the parameters required by leading methods.
Date Issued
2025-06-01
Date Acceptance
2025-03-01
Citation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47 (6), pp.4957-4973
ISSN
0162-8828
Publisher
Institute of Electrical and Electronics Engineers
Start Page
4957
End Page
4973
Journal / Book Title
IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume
47
Issue
6
Copyright Statement
Copyright © 2025 IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/40048344
Publication Status
Published
Coverage Spatial
United States
Date Publish Online
2025-03-06