Research map / Image generation / Editing and style transfer
DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network
Yeying Jin, Aashish Sharma, Robby T. Tan
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 boundary smoothness loss (ablation) | DC-ShadowNet · SRD | RMSE all: 4.72 -> 4.66 | Improved |
| add shadow-robust feature loss (ablation) | DC-ShadowNet · SRD | RMSE all: 4.83 -> 4.66 | Improved |
| add shadow-free chromaticity loss (ablation) | DC-ShadowNet · SRD | RMSE all: 5.05 -> 4.66 | Improved |
| add domain classifier to the generator (ablation) | DC-ShadowNet · SRD | RMSE all: 5.20 -> 4.66 | Improved |
| add domain classifier to the discriminator (ablation) | DC-ShadowNet · SRD | RMSE all: 5.49 -> 4.66 | Improved |
| add both domain classifiers (ablation) | DC-ShadowNet · SRD | RMSE shadow: 16.10 -> 7.70 | Improved |
| add both domain classifiers (ablation) | DC-ShadowNet · SRD | RMSE non-shadow: 4.80 -> 3.39 | Improved |
| add boundary smoothness loss (ablation) | DC-ShadowNet · SRD | RMSE shadow: 7.80 -> 7.70 | Improved |
| add test-time training on test images with unsupervised losses | DC-ShadowNet · LRSS | RMSE: 3.48 -> 3.36 | Improved |
| add test-time training on test images with unsupervised losses | DC-ShadowNet · LRSS | PSNR: 31.01 -> 31.31 | Improved |
| use DC-ShadowNet instead of Mask-ShadowGAN unpaired baseline | unpaired shadow removal · SRD | RMSE shadow: 11.46 -> 7.70 | Improved |
| use DC-ShadowNet instead of Mask-ShadowGAN unpaired baseline | unpaired shadow removal · AISTD | RMSE shadow: 12.5 -> 10.3 | Improved |
Later papers that compared with this method
1 later accepted paper reports DCShadowNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Towards Image Ambient Lighting Normalization (ECCV 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Mask-ShadowGAN — Mask-ShadowGAN: Learning to Remove Shadows From Unpaired Data (ICCV 2019) · 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
- Physics-Based Shadow Image Decomposition for Shadow Removal (TPAMI 2021 · similarity 0.92)
- Shadow Removal via Shadow Image Decomposition (ICCV 2019 · similarity 0.90)
- From Shadow Segmentation to Shadow Removal (ECCV 2020 · similarity 0.90)
- When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data (AAAI 2025 · similarity 0.88)
- SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal (CVPR 2025 · similarity 0.87)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.87)
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.
