Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

Sen DENG, Yidan FENG, Mingqiang WEI*, Haoran XIE*, Yiping CHEN, Jonathan LI, Xiao-ping ZHANG, Jing QIN

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.
Original languageEnglish
Title of host publicationProceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21)
EditorsZhi-Hua ZHOU
PublisherInternational Joint Conferences on Artificial Intelligence
Pages650-656
Number of pages7
ISBN (Electronic)9780999241196
DOIs
Publication statusPublished - Aug 2021
EventThirtieth International Joint Conference on Artificial Intelligence {IJCAI-21} - Montreal, Canada
Duration: 19 Aug 202127 Aug 2021

Conference

ConferenceThirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}
Country/TerritoryCanada
Period19/08/2127/08/21

Bibliographical note

This work was supported by the National Natural Science Foundation of China (Nos. 62032011, 61502137).

Fingerprint

Dive into the research topics of 'Direction-aware Feature-level Frequency Decomposition for Single Image Deraining'. Together they form a unique fingerprint.

Cite this