Research map / Image generation / Image restoration
High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net
Zinuo Li, Xuhang Chen, Chi-Man Pun, Xiaodong Cun
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 Texture Recovery Module (TRM) for high-frequency components (ablation) | FSENet · SD7K full size | RMSE: 35.92 -> 10.00 | Improved |
| add DFE module (ablation) | FSENet · SD7K full size | RMSE: 29.07 -> 10.00 | Improved |
| add DAT module (ablation) | FSENet · SD7K full size | RMSE: 32.94 -> 10.00 | Improved |
| add shadow synthesis pipeline (alpha composition) (ablation) | FSENet · SD7K full size | RMSE: 21.93 -> 10.00 | Improved |
| add shadow synthesis pipeline (ablation) | FSENet · Kligler full size | RMSE: 15.54 -> 10.60 | Improved |
| use Laplacian pyramid depth 3 instead of the default (ablation) | FSENet · SD7K full size | RMSE: 10.00 -> 24.02 | Hurt |
| remove TRM on Kligler (ablation) | FSENet · Kligler full size | PSNR: 27.10 vs 28.98 full; ablation variant PSNR higher than Depth=3 variant | Mixed |
| use FSENet instead of ShadowFormer at full resolution | SD7K full size · SD7K full size | RMSE: 19.79 -> 10.00 | Improved |
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.
- MaskGAN — MaskGAN: Better Text Generation via Filling in the _______ (ICLR 2018) · better on 2 of 3 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
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · similarity 0.85)
- Detail-Preserving Latent Diffusion for Stable Shadow Removal (CVPR 2025 · similarity 0.84)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.84)
- Recasting Regional Lighting for Shadow Removal (AAAI 2024 · similarity 0.84)
- Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model (AAAI 2024 · similarity 0.84)
- Hierarchical Adaptive Filtering Network for Text Image Specular Highlight Removal (CVPR 2025 · similarity 0.83)
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.
