Research map / Image generation / Image restoration
Leveraging Inpainting for Single-Image Shadow Removal
Xiaoguang Li, Qing Guo, Rabab Abdelfattah, Di Lin, Wei Feng, Ivor Tsang, Song Wang
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 inpainting pretraining before shadow removal fine-tuning (ablation) | naive encoder-decoder · ISTD+ | RMSE (all): 4.216 -> 3.527 | Improved |
| add adaptive fusion block (ablation) | two-encoder shadow removal network · ISTD+ | RMSE (all): 3.627 -> 3.398 | Improved |
| use two separate encoders instead of concatenating shadow and masked inputs (ablation) | adaptive fusion network · ISTD+ | RMSE (all): 3.581 -> 3.398 | Improved |
| combine shadow removal with inpainting rather than de-shadowing by inpainting alone (ablation) | adaptive fusion network · ISTD+ | RMSE (all): 5.992 -> 3.398 | Improved |
| add sigmoid to predicted fusion weights (ablation) | adaptive fusion block · ISTD+ | RMSE (all): 3.597 -> 3.398 | Improved |
| keep both weights W1 and W2 in fusion (ablation) | adaptive fusion block · ISTD+ | RMSE (all): 3.432 -> 3.398 (w/o W1); 3.473 -> 3.398 (w/o W2) | Improved |
| pretrain on larger inpainting dataset (full Places2 vs 10^4 images) (ablation) | adaptive fusion network · ISTD+ | RMSE (all): 3.476 -> 3.398 | Improved |
| pretrain on any inpainting dataset (CelebA, Paris-Street-View, Places2 10^4) vs none (ablation) | adaptive fusion network · ISTD+ | RMSE (all): 3.860 -> 3.557 / 3.511 / 3.476 | Improved |
| inpainting-pretrain, then fine-tune on only 10% of ISTD+ | naive encoder-decoder · ISTD+ | RMSE shadow-free / shadow region: 3.07 vs 3.80 (AEFNet); 7.67 vs 7.9 (SP+M-Net) | Improved |
| use longer inpainting pretraining (stronger inpainting model) (ablation) | naive encoder-decoder · ISTD+ | RMSE | Improved |
| add inpainting pretraining (ablation) | naive encoder-decoder · ISTD+ | generalization (RMSE gap, IIW) | Improved |
Closest papers by meaning
- Detail-Preserving Latent Diffusion for Stable Shadow Removal (CVPR 2025 · similarity 0.90)
- When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data (AAAI 2025 · similarity 0.90)
- Shadow-Enlightened Image Outpainting (CVPR 2024 · similarity 0.89)
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · similarity 0.88)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.88)
- Recasting Regional Lighting for Shadow Removal (AAAI 2024 · 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.
