Research map / Image generation / Image restoration
Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
Jifeng Wang, Xiang Li, Jian Yang
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 |
|---|---|---|---|
| Use ST-CGAN instead of scGAN | shadow detection trained on ISTD · SBU | BER (%): 13.26 -> 11.34 | Improved |
| Use ST-CGAN instead of scGAN | shadow detection trained on ISTD · UCF | BER (%): 16.41 -> 16.18 | Improved |
| Use ST-CGAN instead of scGAN | shadow detection trained on ISTD · ISTD | BER (%): 4.7 -> 3.85 | Improved |
| Use ST-CGAN instead of scGAN | shadow detection trained on SBU · SBU | BER (%): 9.1 -> 8.14 | Improved |
| Use ST-CGAN instead of scGAN | shadow detection trained on SBU · UCF | BER (%): 11.5 -> 11.23 | Improved |
| Use ST-CGAN instead of scGAN | shadow detection trained on SBU · ISTD | BER (%): 8.98 -> 7.35 | Improved |
| Use ST-CGAN instead of Gong et al. | shadow removal · ISTD | RMSE (All): 8.53 -> 7.47 | Improved |
| Add discriminator D1 (ablation) | ST-CGAN · ISTD | RMSE (All): 7.51 -> 7.47 | Improved |
| Add discriminator D2 (ablation) | ST-CGAN · ISTD | RMSE (All): 7.56 -> 7.47 | Improved |
| Add generator G1 and discriminator D1 (ablation) | ST-CGAN · ISTD | RMSE (All): 8.19 -> 7.47 | Improved |
| Add discriminator D1 (ablation) | ST-CGAN · ISTD | BER (%): 4.4 -> 3.85 | Improved |
| Add discriminator D2 (ablation) | ST-CGAN · ISTD | BER (%): 4.26 -> 3.85 | Improved |
Closest papers by meaning
- Shadow Detection With Conditional Generative Adversarial Networks (ICCV 2017 · similarity 0.94)
- ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal (ICCV 2019 · similarity 0.93)
- Towards Ghost-Free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN (AAAI 2020 · similarity 0.92)
- Mask-ShadowGAN: Learning to Remove Shadows From Unpaired Data (ICCV 2019 · similarity 0.91)
- 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)
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.
