# A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal

arXiv: https://arxiv.org/abs/2503.01938 · HTML: https://mlsanity.com/paper/2503.01938/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [Hypercolumns for Object Segmentation and Fine-grained Localization](https://mlsanity.com/paper/1411.5752/) (2014)
- [A Model-driven Deep Neural Network for Single Image Rain Removal](https://mlsanity.com/paper/2005.01333/) (2020)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing](https://mlsanity.com/paper/2004.10078/) (2020)
- [Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements](https://mlsanity.com/paper/1904.00637/) (2019)
- [Convolutional Neural Networks Analyzed via Convolutional Sparse Coding](https://mlsanity.com/paper/1607.08194/) (2016)
- [Location-aware Single Image Reflection Removal](https://mlsanity.com/paper/2012.07131/) (2020)
- [WINNet: Wavelet-inspired Invertible Network for Image Denoising](https://mlsanity.com/paper/2109.06381/) (2021)
- [CRRN: Multi-Scale Guided Concurrent Reflection Removal Network](https://mlsanity.com/paper/1805.11802/) (2018)
- [Ada-LISTA: Learned Solvers Adaptive to Varying Models](https://mlsanity.com/paper/2001.08456/) (2020)
- [Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance](https://mlsanity.com/paper/2012.00945/) (2020)
- [Fast Single Image Reflection Suppression via Convex Optimization](https://mlsanity.com/paper/1903.03889/) (2019)
- [Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images](https://mlsanity.com/paper/2010.04324/) (2020)
- [Robust Reflection Removal with Flash-only Cues in the Wild](https://mlsanity.com/paper/2211.02914/) (2022)
- [LINN: Lifting Inspired Invertible Neural Network for Image Denoising](https://mlsanity.com/paper/2105.03303/) (2021)
- [Mixed X-Ray Image Separation for Artworks with Concealed Designs](https://mlsanity.com/paper/2201.09167/) (2022)

## Built on by (most cited first, 7 of 7)

- [GFRRN: Explore the Gaps in Single Image Reflection Removal](https://mlsanity.com/paper/2602.22695/) (2026)
- [ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation](https://mlsanity.com/paper/2601.17468/) (2026)
- [CLUENet: Cluster Attention Makes Neural Networks Have Eyes](https://mlsanity.com/paper/2512.06345/) (2025)
- [Combined Dictionary Unfolding Network with Gradient-Adaptive Fidelity for Transferable Multi-Source Fusion](https://mlsanity.com/paper/2605.00461/) (2026)
- [Principled Reflection Separation via Nonlinear Superposition and Feature Interaction](https://mlsanity.com/paper/2606.02831/) (2026)
- [LowAux-RDNet: Low-Pass Residual Supervision with Scene-Balanced Real-World Training for Single-Image Reflection Removal](https://mlsanity.com/paper/2607.22707/) (2026)
- [MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering](https://mlsanity.com/paper/2608.15096/) (2026)

## Abstract (arXiv)

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.