SDDNet : Style-guided Dual-layer Disentanglement Network for Shadow Detection

Runmin CONG, Yuchen GUAN, Jinpeng CHEN*, Wei ZHANG, Yao ZHAO, Sam KWONG

*Corresponding author for this work

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


Despite significant progress in shadow detection, current methods still struggle with the adverse impact of background color, which may lead to errors when shadows are present on complex backgrounds. Drawing inspiration from the human visual system, we treat the input shadow image as a composition of a background layer and a shadow layer, and design a Style-guided Dual-layer Disentanglement Network (SDDNet) to model these layers independently. To achieve this, we devise a Feature Separation and Recombination (FSR) module that decomposes multi-level features into shadow-related and background-related components by offering specialized supervision for each component, while preserving information integrity and avoiding redundancy through the reconstruction constraint. Moreover, we propose a Shadow Style Filter (SSF) module to guide the feature disentanglement by focusing on style differentiation and uniformization. With these two modules and our overall pipeline, our model effectively minimizes the detrimental effects of background color, yielding superior performance on three public datasets with a real-time inference speed of 32 FPS. Our code is publicly available at:
Original languageEnglish
Title of host publicationMM '23: Proceedings of the 31st ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery (ACM)
ISBN (Print)9798400701085
Publication statusPublished - 27 Oct 2023
EventThe 31st ACM International Conference on Multimedia - Ottawa, Canada
Duration: 29 Oct 20233 Nov 2023


ConferenceThe 31st ACM International Conference on Multimedia
Abbreviated titleMM '23


Dive into the research topics of 'SDDNet : Style-guided Dual-layer Disentanglement Network for Shadow Detection'. Together they form a unique fingerprint.

Cite this