Research map / Detection and segmentation / CNN features
DeshadowNet: A Multi-Context Embedding Deep Network for Shadow Removal
Liangqiong Qu, Jiandong Tian, Shengfeng He, Yandong Tang, Rynson W. H. Lau
Check 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 |
|---|---|---|---|
| Use multi-context DeshadowNet instead of Gong et al. [12] | Shadow removal · UIUC [15] (All) | RMSE: 6.6 -> 5.9 | Improved |
| Use multi-context DeshadowNet instead of Gong et al. [12] | Shadow removal · LRSS [14] (All) | RMSE: 10.43 -> 7.56 | Improved |
| Use multi-context DeshadowNet instead of Gong et al. [12] | Shadow removal · SRD (All) | RMSE: 8.73 -> 6.64 | Improved |
| Use multi-context DeshadowNet instead of Gong et al. [12] | Shadow removal · UIUC [15] (All) | SSIM: 0.9769 -> 0.9832 | Improved |
| Use multi-context DeshadowNet instead of Gong et al. [12] | Shadow removal · LRSS [14] (All) | SSIM: 0.9478 -> 0.9763 | Improved |
| Use multi-context DeshadowNet instead of Gong et al. [12] | Shadow removal · SRD (All) | SSIM: 0.9509 -> 0.9735 | Improved |
| Add G-Net global features and context to S-Net (ablation) | DeshadowNet · UIUC [15] (All) | RMSE: 7.90 -> 5.9 | Improved |
| Add S-Net semantic modeling to G-Net+A-Net (ablation) | DeshadowNet · UIUC [15] (All) | RMSE: 6.7 -> 5.9 | Improved |
| Add A-Net appearance modeling to G-Net+S-Net (ablation) | DeshadowNet · UIUC [15] (All) | RMSE: 6.2 -> 5.9 | Improved |
Later papers that compared with this method
3 later accepted papers report DeshadowNet as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- CANet: A Context-Aware Network for Shadow Removal (ICCV 2021 · better on 2 of 2 shared results)
- Direction-Aware Spatial Context Features for Shadow Detection and Removal (TPAMI 2019 · better on 1 of 1 shared result)
- Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection (ECCV 2018 · 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 0.90)
- Shadow Removal via Shadow Image Decomposition (ICCV 2019 · similarity 0.90)
- Towards Ghost-Free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN (AAAI 2020 · similarity 0.90)
- Efficient Model-Driven Network for Shadow Removal (AAAI 2022 · similarity 0.90)
- DeS3: Adaptive Attention-Driven Self and Soft Shadow Removal Using ViT Similarity (AAAI 2024 · similarity 0.88)
- SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal (CVPR 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.
