Papers › A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal
A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal
Jun-Jie Huang, Tianrui Liu, Zihan Chen, Xinwang Liu, Meng Wang, Pier Luigi Dragotti
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.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Reflection Removal | Real20 | DExNet | PSNR | 23.50 | #5 of 8 | Archive leaderboard | report |
| Reflection Removal | Real20 | DExNet | SSIM | 0.817 | #5 of 8 | Archive leaderboard | report |
| Reflection Removal | SIR^2(Objects) | DExNet | PSNR | 26.38 | #2 of 7 | Archive leaderboard | report |
| Reflection Removal | SIR^2(Objects) | DExNet | SSIM | 0.916 | #2 of 7 | Archive leaderboard | report |
| Reflection Removal | SIR^2(Postcard) | DExNet | PSNR | 25.52 | #2 of 6 | Archive leaderboard | report |
| Reflection Removal | SIR^2(Postcard) | DExNet | SSIM | 0.918 | #2 of 6 | Archive leaderboard | report |
| Reflection Removal | SIR^2(Wild) | DExNet | PSNR | 26.95 | #2 of 6 | Archive leaderboard | report |
| Reflection Removal | SIR^2(Wild) | DExNet | SSIM | 0.908 | #2 of 6 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections