mlsanityData to 7 Oct 2026

CNSNet: A Cleanness-Navigated-Shadow Network for Shadow Removal

arXiv 2209.02174 ↗First posted 6 Sep 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

The key to shadow removal is recovering the contents of the shadow regions with the guidance of the non-shadow regions. Due to the inadequate long-range modeling, the CNN-based approaches cannot thoroughly investigate the information from the non-shadow regions. To solve this problem, we propose a novel cleanness-navigated-shadow network (CNSNet), with a shadow-oriented adaptive normalization (SOAN) module and a shadow-aware aggregation with transformer (SAAT) module based on the shadow mask. Under the guidance of the shadow mask, the SOAN module formulates the statistics from the non-shadow region and adaptively applies them to the shadow region for region-wise restoration. The SAAT module utilizes the shadow mask to precisely guide the restoration of each shadowed pixel by considering the highly relevant pixels from the shadow-free regions for global pixel-wise restoration. Extensive experiments on three benchmark datasets (ISTD, ISTD+, and SRD) show that our method achieves superior de-shadowing performance.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 6 Sep 2022.

Builds on

32 of 54 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2017Non-local Neural Networkscited by 2,290
  7. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  8. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  9. 2020Pre-Trained Image Processing Transformercited by 891
  10. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  11. 2022Vision Transformers for Single Image Dehazingcited by 255
  12. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
20 more
  1. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 236
  2. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 160
  3. 2019Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GANcited by 102
  4. 2019Shadow Removal via Shadow Image Decompositioncited by 96
  5. 2019Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Datacited by 91
  6. 2021Auto-Exposure Fusion for Single-Image Shadow Removalcited by 78
  7. 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
  8. 2022DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Networkcited by 68
  9. 2020From Shadow Segmentation to Shadow Removalcited by 59
  10. 2018Direction-aware Spatial Context Features for Shadow Detection and Removalcited by 58
  11. 2019Region Normalization for Image Inpaintingcited by 54
  12. 2021From Shadow Generation to Shadow Removalcited by 54
  13. 2019ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removalcited by 51
  14. 2021CANet: A Context-Aware Network for Shadow Removalcited by 47
  15. 2020Physics-based Shadow Image Decomposition for Shadow Removalcited by 38
  16. 2019RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removalcited by 35
  17. 2017Improving Shadow Suppression for Illumination Robust Face Recognitioncited by 29
  18. 2016Interactive Removal and Ground Truth for Difficult Shadow Scenescited by 11
  19. 2022CRFormer: A Cross-Region Transformer for Shadow Removalcited by 7
  20. 2018A Reflectance Based Method For Shadow Detection and Removalcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4.

5 papers.

  1. 2024Single-Image Shadow Removal Using Deep Learning: A Comprehensive Surveycited by 7
  2. 2023SAM-helps-Shadow:When Segment Anything Model meet shadow removalcited by 6
  3. 2024S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removalcited by 6
  4. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 6
  5. 2024Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removalcited by 0