A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal
Authors:
- Jun-Jie HuangJHJun-Jie Huang
- Tianrui LiuTLTianrui Liu
- Zihan ChenZCZihan Chen
- Xinwang LiuXLXinwang Liu
- Meng WangMWMeng Wang
- Pier Luigi DragottiPDPier Luigi Dragotti
Preprint
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.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Two-stage single image reflection removal with reflection-aware guidanceApplied Intelligence, 2023
- Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image ProcessingIEEE Signal Processing Magazine, 2021
- Efficient and Interpretable Deep Blind Image Deblurring Via Algorithm UnrollingIEEE Transactions on Computational Imaging, 2020
- Mirror, Mirror, on the Wall, Who’s Got the Clearest Image of Them All?—A Tailored Approach to Single Image Reflection RemovalIEEE Transactions on Image Processing, 2019
- Single Image Reflection Removal Using Convolutional Neural NetworksIEEE Transactions on Image Processing, 2018
- Region-Aware Reflection Removal With Unified Content and Gradient PriorsIEEE Transactions on Image Processing, 2018
- Handbook of Blind Source Separation: Independent Component Analysis and Applications (Common, P. and Jutten, ; 2010 [Book Review]IEEE Signal Processing Magazine, 2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Blind signal separation: statistical principlesProceedings of the IEEE, 1998