mlsanityData to 14 Oct 2026

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

arXiv 2308.08935 ↗First posted 17 Aug 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 32 of its 68 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

32 of 68 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  6. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 161
  7. 2019Shadow Removal via Shadow Image Decompositioncited by 98
  8. 2019Rendering Synthetic Objects into Legacy Photographscited by 72
  9. 2020Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Imagescited by 61
  10. 2018Direction-aware Spatial Context Features for Shadow Detection and Removalcited by 58
  11. 2020RGB-D Salient Object Detection with Cross-Modality Modulation and Selectioncited by 50
  12. 2023PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminatorscited by 49
20 more
  1. 2020DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detectioncited by 45
  2. 2017A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuationcited by 39
  3. 2022CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detectioncited by 38
  4. 2019Instance Shadow Detectioncited by 37
  5. 2022Does Thermal Really Always Matter for RGB-T Salient Object Detection?cited by 37
  6. 2019Revisiting Shadow Detection: A New Benchmark Dataset for Complex Worldcited by 34
  7. 2021Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detectioncited by 34
  8. 2021RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Imagescited by 34
  9. 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
  10. 2022Global-and-Local Collaborative Learning for Co-Salient Object Detectioncited by 24
  11. 2021Triple-cooperative Video Shadow Detectioncited by 22
  12. 2022A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labelscited by 20
  13. 2021Unsupervised Portrait Shadow Removal via Generative Priorscited by 16
  14. 2022BCS-Net: Boundary, Context and Semantic for Automatic COVID-19 Lung Infection Segmentation from CT Imagescited by 16
  15. 2022Multi-Projection Fusion and Refinement Network for Salient Object Detection in 360deg Omnidirectional Imagecited by 13
  16. 2022Video Shadow Detection via Spatio-Temporal Interpolation Consistency Trainingcited by 12
  17. 2022PSNet: Parallel Symmetric Network for Video Salient Object Detectioncited by 12
  18. 2022Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Datacited by 11
  19. 2021Fine-Context Shadow Detection using Shadow Removalcited by 9
  20. 2020Task-Feature Collaborative Learning with Application to Personalized Attribute Predictioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 2; 2026: 3.

11 papers.

  1. 2024Language-Driven Interactive Shadow Detectioncited by 7
  2. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 7
  3. 2024Timeline and Boundary Guided Diffusion Network for Video Shadow Detectioncited by 6
  4. 2025Deep Learning in Concealed Dense Predictioncited by 6
  5. 2023AdapterShadow: Adapting Segment Anything Model for Shadow Detectioncited by 5
  6. 2024TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Taskscited by 5
  7. 2026LGTM: Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulationcited by 1
  8. 2024RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verificationcited by 0
  9. 2025DTTNet: Improving Video Shadow Detection via Dark-Aware Guidance and Tokenized Temporal Modelingcited by 0
  10. 2026SARU: A Shadow-Aware and Removal Unified Framework for Remote Sensing Images with New Benchmarkscited by 0
  11. 2026Consistency as Regularization for Unsupervised Shadow Removalcited by 0