mlsanityData to 14 Oct 2026

Shadow Removal via Shadow Image Decomposition

arXiv 1908.08628 ↗First posted 23 Aug 2019cs.CVcited by 98

Not on the map. Why?

Abstract (arXiv)

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects on the images. We train and test our framework on the most challenging shadow removal dataset (ISTD). Compared to the state-of-the-art method, our model achieves a 40% error reduction in terms of root mean square error (RMSE) for the shadow area, reducing RMSE from 13.3 to 7.9. Moreover, we create an augmented ISTD dataset based on an image decomposition system by modifying the shadow parameters to generate new synthetic shadow images. Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7.4.

Key facts. Cited by 98 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 12; 2023: 16; 2024: 29; 2025: 14; 2026: 15.

98 papers.

Sort:

By area:

  1. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 109
  2. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 103
  3. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  4. 2021Auto-Exposure Fusion for Single-Image Shadow Removalcited by 79
  5. 2024ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertioncited by 71
  6. 2022DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Networkcited by 69
  7. 2023Residual Denoising Diffusion Modelscited by 69
  8. 2021From Shadow Generation to Shadow Removalcited by 55
  9. 2021CANet: A Context-Aware Network for Shadow Removalcited by 47
  10. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  11. 2022DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similaritycited by 38
  12. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
38 more
  1. 2023ShadowFormer: Global Context Helps Image Shadow Removalcited by 35
  2. 2023Latent Feature-Guided Diffusion Models for Shadow Removalcited by 29
  3. 2021Learning from Synthetic Shadows for Shadow Detection and Removalcited by 27
  4. 2023Leveraging Inpainting for Single-Image Shadow Removalcited by 25
  5. 2024Recasting Regional Lighting for Shadow Removalcited by 23
  6. 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22
  7. 2024ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformercited by 20
  8. 2023Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noisecited by 19
  9. 2024OmniSR: Shadow Removal under Direct and Indirect Lightingcited by 19
  10. 2021Blind Image Decompositioncited by 18
  11. 2021Unsupervised Portrait Shadow Removal via Generative Priorscited by 16
  12. 2024Detail-Preserving Latent Diffusion for Stable Shadow Removalcited by 13
  13. 2024Taming Diffusion Models for Image Restoration: A Reviewcited by 12
  14. 2024Regional Attention for Shadow Removalcited by 12
  15. 2022Shadow-Aware Dynamic Convolution for Shadow Removalcited by 11
  16. 2023SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detectioncited by 11
  17. 2024Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attackscited by 10
  18. 2024Diff-Shadow: Global-guided Diffusion Model for Shadow Removalcited by 10
  19. 2021Fine-Context Shadow Detection using Shadow Removalcited by 9
  20. 2024Towards Image Ambient Lighting Normalizationcited by 9
  21. 2022CRFormer: A Cross-Region Transformer for Shadow Removalcited by 8
  22. 2023Memory augment is All You Need for image restorationcited by 8
  23. 2022SpA-Former: Transformer image shadow detection and removal via spatial attentioncited by 7
  24. 2024ShadowMaskFormer: Mask Augmented Patch Embeddings for Shadow Removalcited by 7
  25. 2024Single-Image Shadow Removal Using Deep Learning: A Comprehensive Surveycited by 7
  26. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 7
  27. 2021Repopulating Street Scenescited by 6
  28. 2023SAM-helps-Shadow:When Segment Anything Model meet shadow removalcited by 6
  29. 2024S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removalcited by 6
  30. 2021Temporal Feature Warping for Video Shadow Detectioncited by 5
  31. 2022CNSNet: A Cleanness-Navigated-Shadow Network for Shadow Removalcited by 5
  32. 2023LP-IOANet: Efficient High Resolution Document Shadow Removalcited by 5
  33. 2024Shadow Removal Refinement via Material-Consistent Shadow Edgescited by 5
  34. 2024MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesiscited by 5
  35. 2025DenseSR: Image Shadow Removal as Dense Predictioncited by 5
  36. 2025UniSER: A Foundation Model for Unified Soft Effects Removalcited by 5
  37. 2024FieldNet: Efficient Real-Time Shadow Removal for Enhanced Vision in Field Roboticscited by 4
  38. 2024SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removalcited by 4

50 most cited of 98 All 98 (JSON)