Research map / Detection and segmentation / CNN features
Adaptive Illumination Mapping for Shadow Detection in Raw Images
Jiayu Sun, Ke Xu, Youwei Pang, Lihe Zhang, Huchuan Lu, Gerhard Hancke, Rynson Lau
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 |
|---|---|---|---|
| train on raw images instead of sRGB images | proposed shadow detector · SARA | BER: 2.97 -> 2.61 | Improved |
| raw input versus sRGB on non-shadow region error | proposed shadow detector · SARA | non-shadow error: 1.16 -> 1.47 | Hurt |
| train existing detectors on raw images | BDRAR, MTMT, FDRNet, SID · SARA | BER: BDRAR 3.91 -> 4.34; MTMT 3.65 -> 4.79; FDRNet 7.55 -> 5.46; SID 7.71 -> 8.9 | Mixed |
| add adaptive illumination mapping (AIM) module (ablation) | shadow detection module · SARA | BER: 3.19 -> 2.92 | Improved |
| add feedback mechanism (ablation) | SDM+AIM · SARA | BER: 2.92 -> 2.86 | Improved |
| add feature discrepancy loss Ld (ablation) | SDM+AIM+FM · SARA | BER: 2.86 -> 2.70 | Improved |
| add shadow error map (ablation) | SDM+AIM+FM+Ld · SARA | BER: 2.70 -> 2.61 | Improved |
| add feedback mechanism (ablation) | SDM+AIM · SBU | BER: 3.01 -> 3.00 | No clear effect |
| add AIM module (ablation) | shadow detection module · SBU | BER: 3.39 -> 3.01 | Improved |
| use saliency detectors (LGSL, SAMNet) for shadow detection | salient object detection methods · SARA | shadow region error: 27.97 (LGSL) vs 1.22 non-shadow | Hurt |
Closest papers by meaning
- Recasting Regional Lighting for Shadow Removal (AAAI 2024 · similarity 0.86)
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · similarity 0.85)
- MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis (CVPR 2025 · similarity 0.85)
- DeS3: Adaptive Attention-Driven Self and Soft Shadow Removal Using ViT Similarity (AAAI 2024 · similarity 0.84)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.84)
- OmniSR: Shadow Removal Under Direct and Indirect Lighting (AAAI 2025 · similarity 0.84)
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.
