Research map / Image generation / Image restoration
Mask-ShadowGAN: Learning to Remove Shadows From Unpaired Data
Xiaowei Hu, Yitong Jiang, Chi-Wing Fu, Pheng-Ann Heng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add shadow-mask guided generation (Mask-ShadowGAN) instead of plain CycleGAN | unpaired shadow removal · SRD | RMSE: 9.14 -> 7.32 | Improved |
| add shadow-mask guided generation instead of plain CycleGAN | unpaired shadow removal · ISTD | RMSE: 8.16 -> 7.61 | Improved |
| train on unpaired data instead of paired data (DSC) | shadow removal · SRD | RMSE: 6.21 -> 7.32 | Hurt |
| train on unpaired data instead of paired data (DSC) | shadow removal · ISTD | RMSE: 6.67 -> 7.61 | Hurt |
| use unpaired learned model instead of hand-crafted prior methods (Gong et al.) | shadow removal · ISTD | RMSE: 8.53 -> 7.61 | Improved |
| train on the diverse unpaired USR set instead of paired DSC trained models | Mask-ShadowGAN · USR test set | user rating: 4.78 -> 6.30 | Improved |
| train Mask-ShadowGAN unpaired on ISTD instead of DSC on the same data | shadow removal · USR test set | user rating: 2.38 -> 4.07 | Improved |
| train Mask-ShadowGAN unpaired on SRD instead of DSC on the same data | shadow removal · USR test set | user rating: 2.93 -> 3.38 | Improved |
| train on USR instead of on ISTD | Mask-ShadowGAN · USR test set | user rating: 4.07 -> 6.30 | Improved |
Later papers that compared with this method
2 later accepted papers report Mask-ShadowGAN as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Shadow Generation for Composite Image in Real-World Scenes (AAAI 2022 · better on 1 of 1 shared result)
- DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network (ICCV 2021 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal (CVPR 2018 · similarity 0.91)
- From Shadow Segmentation to Shadow Removal (ECCV 2020 · similarity 0.91)
- SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal (CVPR 2025 · similarity 0.89)
- When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data (AAAI 2025 · similarity 0.88)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.87)
- OmniSR: Shadow Removal Under Direct and Indirect Lighting (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
