A Wavelet-guided Deep Unfolding Network for Single Image Reflection Removal.

Journal: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Published Date: Jun 26, 2025

Abstract

Removing unwanted reflections from images is a fundamental yet challenging problem in low-level computer vision. Recent deep learning-based Single Image Reflection Removal (SIRR) methods have made significant progress. However, separating reflections from transmission content remains difficult, particularly in complex scenes where the two exhibit high visual similarity. Upon careful analysis, we find that reflections predominantly reside in the high-frequency components of an image. These reflections tend to distort fine details in the high-frequency range, while the low-frequency information remains relatively less affected. This observation motivates us to explore a frequency-aware approach for SIRR by leveraging the Discrete Wavelet Transform (DWT). The wavelet decomposition enables us to distinguish and isolate reflective artifacts in the frequency domain while preserving the transmission information. Building on this insight, we propose a novel Wavelet-guided Deep Unfolding Network (WDUNet) that leverages the strengths of wavelet decomposition and deep unfolding techniques to improve interpretability and generalization in SIRR. Specifically, we formulate an optimization-based reflection removal model using DWT and convolutional dictionaries. The proposed model is optimized via a proximal gradient algorithm and then unfolded into a neural network architecture, where all parameters are learned end-to-end during training. By combining wavelet domain analysis with deep unfolding, WDUNet enhances both the interpretability and generalization of SIRR methods. Additionally, we design and integrate the Low-frequency Parameter Estimation Module (LPEM) and High-frequency Parameter Estimation Module (HPEM) modules into WDUNet, allowing the network to automatically learn and optimize the models' hyperparameters. Extensive experiments conducted on four benchmark datasets demonstrate that WDUNet consistently outperforms existing state-of-the-art methods in both objective evaluation metrics and subjective visual quality.

Authors

  • Ya-Nan Zhang
    Chongqing Key Laboratory of Image cognition, Chongqing University of Posts and Telecommunications, Chongqing 400065, China; College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China. Electronic address: zyn962464@gmail.com.
  • Qiufu Li
  • Xu Wu
    University of Shanghai for Science and Technology, Terahertz Technology Innovation Research Institute, Shanghai Key Lab of Modern Optical System, Shanghai Institute of Intelligent Science and Technology, Shanghai, 200093, China.
  • Nan Mu
    Dept. of Biomedical Engineering, Michigan Technological University, 1400 Townsend Drive Houghton, Michigan 49931, USA.
  • Xiaoning Li
    The First Affiliated Hospital, Wannan Medical College, Wuhu, Anhui, China.
  • Linlin Shen

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals