Real-World Image Deraining Using Model-Free Unsupervised Learning

We propose a novel model-free unsupervised learning paradigm to tackle the unfavorable prevailing problem of real-world image deraining, dubbed MUL-Derain. Beyond existing unsupervised deraining efforts, MUL-Derain leverages a model-free Multiscale Attentive Filtering (MSAF) to handle multiscale rai...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of intelligent systems Vol. 2024
Main Authors Yu, Rongwei, Xiang, Jingyi, Ni Shu, Zhang, Peihao, Li, Yizhan, Shen, Yiyang, Wang, Weiming, Wang, Lina
Format Journal Article
LanguageEnglish
Published New York Hindawi Limited 26.08.2024
Subjects
Paradigms
Rain
Unsupervised learning
Online AccessGet full text

Cover

More Information
Summary:We propose a novel model-free unsupervised learning paradigm to tackle the unfavorable prevailing problem of real-world image deraining, dubbed MUL-Derain. Beyond existing unsupervised deraining efforts, MUL-Derain leverages a model-free Multiscale Attentive Filtering (MSAF) to handle multiscale rain streaks. Therefore, formulation of any rain imaging is not necessary, and it requires neither iterative optimization nor progressive refinement operations. Meanwhile, MUL-Derain can efficiently compute spatial coherence and global interactions by modeling long-range dependencies, allowing MSAF to learn useful knowledge from a larger or even global rain region. Furthermore, we formulate a novel multiloss function to constrain MUL-Derain to preserve both color and structure information from the rainy images. Extensive experiments on both synthetic and real-world datasets demonstrate that our MUL-Derain obtains state-of-the-art performance over un/semisupervised methods and exhibits competitive advantages over the fully-supervised ones.
ISSN:0884-8173
1098-111X
DOI:10.1155/2024/7454928