mlsanityData to 14 Oct 2026

Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data

arXiv 1903.10683 ↗First posted 26 Mar 2019cs.CV cs.MMcited by 92

Not on the map. Why?

Abstract (arXiv)

This paper presents a new method for shadow removal using unpaired data, enabling us to avoid tedious annotations and obtain more diverse training samples. However, directly employing adversarial learning and cycle-consistency constraints is insufficient to learn the underlying relationship between the shadow and shadow-free domains, since the mapping between shadow and shadow-free images is not simply one-to-one. To address the problem, we formulate Mask-ShadowGAN, a new deep framework that automatically learns to produce a shadow mask from the input shadow image and then takes the mask to guide the shadow generation via re-formulated cycle-consistency constraints. Particularly, the framework simultaneously learns to produce shadow masks and learns to remove shadows, to maximize the overall performance. Also, we prepared an unpaired dataset for shadow removal and demonstrated the effectiveness of Mask-ShadowGAN on various experiments, even it was trained on unpaired data.

Key facts. Cited by 92 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 15; 2023: 16; 2024: 25; 2025: 14; 2026: 12.

92 papers.

Sort:

By area:

  1. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 103
  2. 2021Auto-Exposure Fusion for Single-Image Shadow Removalcited by 79
  3. 2024ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertioncited by 71
  4. 2022DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Networkcited by 69
  5. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  6. 2021From Shadow Generation to Shadow Removalcited by 55
  7. 2021CANet: A Context-Aware Network for Shadow Removalcited by 47
  8. 2022DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similaritycited by 38
  9. 2023High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Netcited by 36
  10. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  11. 2023ShadowFormer: Global Context Helps Image Shadow Removalcited by 35
  12. 2023Latent Feature-Guided Diffusion Models for Shadow Removalcited by 29
38 more
  1. 2021Learning from Synthetic Shadows for Shadow Detection and Removalcited by 27
  2. 2023Leveraging Inpainting for Single-Image Shadow Removalcited by 25
  3. 2024Recasting Regional Lighting for Shadow Removalcited by 23
  4. 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22
  5. 2022Controllable Shadow Generation Using Pixel Height Mapscited by 22
  6. 2024OmniSR: Shadow Removal under Direct and Indirect Lightingcited by 19
  7. 2022Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learningcited by 18
  8. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  9. 2021Unsupervised Portrait Shadow Removal via Generative Priorscited by 16
  10. 2022SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Taskscited by 15
  11. 2022UDoc-GAN: Unpaired Document Illumination Correction with Background Light Priorcited by 15
  12. 2023PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositingcited by 15
  13. 2024Detail-Preserving Latent Diffusion for Stable Shadow Removalcited by 13
  14. 2024Regional Attention for Shadow Removalcited by 12
  15. 2021Deep Image-based Illumination Harmonizationcited by 11
  16. 2025ORIDa: Object-centric Real-world Image Composition Datasetcited by 11
  17. 2023DocDeshadower: Frequency-Aware Transformer for Document Shadow Removalcited by 9
  18. 2024Towards Image Ambient Lighting Normalizationcited by 9
  19. 2022CRFormer: A Cross-Region Transformer for Shadow Removalcited by 8
  20. 2023Memory augment is All You Need for image restorationcited by 8
  21. 2024Learning Image Demoireing from Unpaired Real Datacited by 8
  22. 2022SpA-Former: Transformer image shadow detection and removal via spatial attentioncited by 7
  23. 2024ShadowMaskFormer: Mask Augmented Patch Embeddings for Shadow Removalcited by 7
  24. 2024Single-Image Shadow Removal Using Deep Learning: A Comprehensive Surveycited by 7
  25. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 7
  26. 2021Repopulating Street Scenescited by 6
  27. 2023SAM-helps-Shadow:When Segment Anything Model meet shadow removalcited by 6
  28. 2024S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removalcited by 6
  29. 2022CNSNet: A Cleanness-Navigated-Shadow Network for Shadow Removalcited by 5
  30. 2024Shadow Removal Refinement via Material-Consistent Shadow Edgescited by 5
  31. 2024MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesiscited by 5
  32. 2024FieldNet: Efficient Real-Time Shadow Removal for Enhanced Vision in Field Roboticscited by 4
  33. 2024SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removalcited by 4
  34. 2024ShadowHack: Hacking Shadows via Luminance-Color Divide and Conquercited by 4
  35. 2025After the Party: Navigating the Mapping From Color to Ambient Lightingcited by 4
  36. 2021Benchmarking Shadow Removal for Facial Landmark Detection and Beyondcited by 3
  37. 2023Structure-Informed Shadow Removal Networkscited by 3
  38. 2023Learning Physical-Spatio-Temporal Features for Video Shadow Removalcited by 3

50 most cited of 92 All 92 (JSON)