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

08/17/2023
by   Runmin Cong, et al.
Shandong University
City University of Hong Kong
BEIJING JIAOTONG UNIVERSITY
Tsinghua University
0

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.

READ FULL TEXT

page 2

page 4

page 7

page 8

10/05/2022

Inharmonious Region Localization with Auxiliary Style Feature

With the prevalence of image editing techniques, users can create fantas...
12/16/2020

Domain Adaptive Object Detection via Feature Separation and Alignment

Recently, adversarial-based domain adaptive object detection (DAOD) meth...
06/05/2021

Region-aware Adaptive Instance Normalization for Image Harmonization

Image composition plays a common but important role in photo editing. To...
09/13/2022

Time-of-Day Neural Style Transfer for Architectural Photographs

Architectural photography is a genre of photography that focuses on capt...
03/19/2019

Mask-guided Style Transfer Network for Purifying Real Images

Recently, the progress of learning-by-synthesis has proposed a training ...
08/17/2023

Frequency Perception Network for Camouflaged Object Detection

Camouflaged object detection (COD) aims to accurately detect objects hid...
09/15/2023

Efficient Polyp Segmentation Via Integrity Learning

Accurate polyp delineation in colonoscopy is crucial for assisting in di...

Please sign up or login with your details

Forgot password? Click here to reset